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

    Neuronpedia

    INDEX
    Explanations

    code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ast
    -0.07
    audi
    -0.06
    .numpy
    -0.06
    操
    -0.06
     stret
    -0.06
    .market
    -0.06
    /domain
    -0.06
     Απ
    -0.06
    <thead
    -0.06
    Ajax
    -0.06
    POSITIVE LOGITS
    ícul
    0.07
    %),
    0.07
     boundaries
    0.07
     ];
    0.07
     Alerts
    0.06
     seinen
    0.06
     pii
    0.06
    [res
    0.06
     Meter
    0.06
     Alic
    0.06
    Act Density 0.005%

    No Known Activations