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

    Neuronpedia

    INDEX
    Explanations

    Parsing/document structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     webView
    -0.07
     Jad
    -0.06
    -Requested
    -0.06
     sofa
    -0.06
    توان
    -0.06
     Kore
    -0.06
     recurs
    -0.06
     enfrent
    -0.06
    lıyor
    -0.06
    Bomb
    -0.06
    POSITIVE LOGITS
    عمال
    0.07
    行
    0.07
    Real
    0.07
     Farmer
    0.06
    activation
    0.06
    льт
    0.06
     галуз
    0.06
    存
    0.06
    Job
    0.06
    arrays
    0.06
    Act Density 0.000%

    No Known Activations