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

    Neuronpedia

    INDEX
    Explanations

    pickle serialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    благ
    -0.06
    年轻
    -0.06
    仆
    -0.06
    тив
    -0.06
     Herald
    -0.06
    أن
    -0.06
    罗
    -0.06
     watts
    -0.06
    승
    -0.06
    POSITIVE LOGITS
    极速
    0.09
    严禁
    0.08
    _gray
    0.08
    _char
    0.07
    急剧
    0.07
    흕
    0.07
    大的
    0.07
    짤
    0.07
    _peer
    0.07
     Epid
    0.07
    Act Density 0.029%

    No Known Activations