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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with product quality and specifications

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

    items preceding numerical or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.57
    TagMode
    -0.55
    ImageContext
    -0.51
    sidemargin
    -0.48
    InputBorder
    -0.46
     dipende
    -0.46
    addCriterion
    -0.45
    EndContext
    -0.44
    Diweddarwch
    -0.44
    VolleyError
    -0.42
    POSITIVE LOGITS
    important
    0.42
    Notae
    0.40
    rodalom
    0.39
    elfth
    0.38
     برانيه
    0.38
    Famille
    0.38
     autorytatywna
    0.38
     important
    0.38
    /\/
    0.37
    jedis
    0.35
    Act Density 0.004%

    No Known Activations