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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тип
    -0.09
     אצל
    -0.08
     выгод
    -0.08
     techno
    -0.07
    COMM
    -0.07
    /lib
    -0.07
    _SCREEN
    -0.07
     divina
    -0.07
     Communist
    -0.07
     килгән
    -0.07
    POSITIVE LOGITS
     भार
    0.10
     augmentation
    0.09
    .gamma
    0.08
     lourd
    0.08
    .loads
    0.08
     상승
    0.07
    ampling
    0.07
    負
    0.07
     surcharge
    0.07
    最高
    0.07
    Act Density 0.004%

    No Known Activations