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

    Neuronpedia

    INDEX
    Explanations

    }_{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SCHEDULE
    -0.08
    受欢迎
    -0.07
    мин
    -0.07
    辅导
    -0.07
     Aston
    -0.07
     BASE
    -0.07
    .Validation
    -0.07
     vil
    -0.07
     socks
    -0.07
     vast
    -0.07
    POSITIVE LOGITS
     técnica
    0.07
    这件事
    0.07
    personal
    0.07
    cop
    0.07
     CLR
    0.07
    含义
    0.07
    ἰ
    0.07
    �
    0.06
    -B
    0.06
    -do
    0.06
    Act Density 0.009%

    No Known Activations