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

    Neuronpedia

    INDEX
    Explanations

    WIN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ￥
    -0.07
    >()->
    -0.06
    価格
    -0.06
     Bec
    -0.06
    ẩ
    -0.06
    }}">{{$
    -0.06
     mám
    -0.06
    �
    -0.06
    having
    -0.06
     Ang
    -0.06
    POSITIVE LOGITS
     expanded
    0.07
    _watch
    0.07
     Kit
    0.07
    0.07
     birds
    0.07
     котором
    0.07
     初始化
    0.07
    Middle
    0.07
     fucked
    0.06
     feminine
    0.06
    Act Density 0.002%

    No Known Activations