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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tabs
    -0.06
    GRESS
    -0.06
     Athen
    -0.06
     Knife
    -0.06
    加载
    -0.06
     senses
    -0.06
     Ấ
    -0.06
    willReturn
    -0.06
    Executing
    -0.06
    pear
    -0.06
    POSITIVE LOGITS
     maxValue
    0.06
     UNESCO
    0.06
    362
    0.06
     відпов
    0.06
    oredProcedure
    0.06
     cinsel
    0.06
    	re
    0.06
     göç
    0.06
    造成
    0.06
    /Private
    0.06
    Act Density 0.001%

    No Known Activations