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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workforce
    -0.09
     சொல்ல
    -0.09
     told
    -0.08
     поис
    -0.08
    usten
    -0.08
     droom
    -0.08
     dromen
    -0.08
     梦
    -0.08
    aysay
    -0.08
     boodschap
    -0.08
    POSITIVE LOGITS
     fot
    0.08
     Expression
    0.08
    级
    0.08
    Expression
    0.08
     lhs
    0.08
    _EXPR
    0.08
    アン
    0.08
    Modulo
    0.08
     
    0.08
    (expression
    0.08
    Act Density 0.008%

    No Known Activations