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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cor
    -0.07
    COOKIE
    -0.06
     데
    -0.06
    Smooth
    -0.06
    590
    -0.06
    Past
    -0.06
     career
    -0.06
     follic
    -0.06
    Identification
    -0.06
     logistic
    -0.06
    POSITIVE LOGITS
    <ul
    0.08
    。↵↵↵↵
    0.06
    /big
    0.06
    .buy
    0.06
    >,</
    0.06
    >;
    0.06
    두
    0.06
     отправ
    0.06
    isans
    0.05
    .createElement
    0.05
    Act Density 0.213%

    No Known Activations