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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     несп
    -0.06
    _Em
    -0.06
     Laur
    -0.06
     �
    -0.06
     RU
    -0.06
     firmalar
    -0.06
     �
    -0.06
     Tec
    -0.06
     Dum
    -0.06
    atLng
    -0.06
    POSITIVE LOGITS
     spice
    0.07
    meldung
    0.07
    $$$
    0.06
    ipheral
    0.06
     상품
    0.06
     achieving
    0.06
    ポート
    0.06
    ��
    0.06
    fred
    0.06
    ster
    0.06
    Act Density 0.000%

    No Known Activations