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

    Neuronpedia

    INDEX
    Explanations

    override

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ../../../
    -0.08
     witty
    -0.07
     类
    -0.07
     leaks
    -0.07
    .masksToBounds
    -0.07
    .cert
    -0.06
     základ
    -0.06
    ляв
    -0.06
    _testing
    -0.06
    まだ
    -0.06
    POSITIVE LOGITS
    alling
    0.06
    --*/↵
    0.06
    /s
    0.06
     thrilling
    0.06
    .modelo
    0.06
     RM
    0.06
     imposes
    0.06
     unrecognized
    0.06
     個
    0.06
    駅徒歩
    0.06
    Act Density 0.002%

    No Known Activations