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

    Neuronpedia

    INDEX
    Explanations

    views

    np_max-act · gemini-2.0-flash

    The neuron detects expressions of opinion or commentary—tokens that signal someone giving views, thoughts, or personal remarks.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    敬
    -0.07
    _side
    -0.07
     endl
    -0.07
     Snow
    -0.06
    -append
    -0.06
    conto
    -0.06
    .import
    -0.06
    晨报
    -0.06
    ываем
    -0.06
    idue
    -0.06
    POSITIVE LOGITS
     Brake
    0.07
    𒁺
    0.07
     kidding
    0.07
    棪
    0.06
    .DataType
    0.06
    Updates
    0.06
    ,Yes
    0.06
     PAN
    0.06
    相关内容
    0.06
     uart
    0.06
    Act Density 0.077%

    No Known Activations