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

    Neuronpedia

    INDEX
    Explanations

    news updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מסוגל
    -0.08
    �
    -0.07
    ﱢ
    -0.07
     informs
    -0.07
     covid
    -0.07
     lux
    -0.07
    .icons
    -0.07
     Daily
    -0.07
     forged
    -0.07
     espec
    -0.07
    POSITIVE LOGITS
    仍有
    0.07
    _accessor
    0.06
    行使
    0.06
    -x
    0.06
    去
    0.06
    输给
    0.06
    鹙
    0.06
    eneral
    0.06
    操作
    0.06
    還有
    0.06
    Act Density 0.022%

    No Known Activations