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

    Neuronpedia

    INDEX
    Explanations

    equality/inequality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bars
    -0.07
     Kant
    -0.07
     Herbal
    -0.06
    .travel
    -0.06
    交通
    -0.06
    <Data
    -0.06
     maz
    -0.06
     Sticky
    -0.06
    blast
    -0.06
    .getText
    -0.06
    POSITIVE LOGITS
    <>();↵↵
    0.07
     vulnerability
    0.06
     لأ
    0.06
    .AppendLine
    0.06
    /order
    0.06
     клуб
    0.06
    ασία
    0.06
     сопров
    0.06
    任
    0.06
    ::::::::::::
    0.06
    Act Density 0.020%

    No Known Activations