Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or request help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    be + verb or adjective

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects requests or expressions of need/obligation — tokens used when asking for help, stating what should/needs/would be done, or posing a question.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    flashdata
    -0.41
    PreInfinity
    -0.40
    Попис
    -0.39
    SharedCtor
    -0.39
    IsMutable
    -0.39
    #
    -0.38
    stdc
    -0.37
    IntOverflow
    -0.37
    Ӕ
    -0.35
    цездатний
    -0.35
    POSITIVE LOGITS
    +#+#
    0.64
    章节错误
    0.50
    twimg
    0.48
    makeConstraints
    0.48
    页面存档备份
    0.48
     NgModule
    0.46
     StyleSheet
    0.46
    存于互联网档案馆
    0.46
    garder
    0.45
    TypedDataSet
    0.45
    Act Density 0.435%

    No Known Activations