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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swiss
    -0.07
     jiný
    -0.07
     này
    -0.07
    рий
    -0.07
    ξει
    -0.06
    _gain
    -0.06
    сы
    -0.06
    _HOLD
    -0.06
    activated
    -0.06
     chứ
    -0.06
    POSITIVE LOGITS
    atore
    0.08
    %);↵
    0.07
    合わせ
    0.07
    /.↵
    0.07
    OPS
    0.06
     frat
    0.06
     davidjl
    0.06
     IOS
    0.06
    :)];↵
    0.06
    zzarella
    0.06
    Act Density 0.049%

    No Known Activations