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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voting
    -0.07
     obedient
    -0.07
    mas
    -0.07
    aha
    -0.07
    oste
    -0.06
     predictors
    -0.06
    司
    -0.06
     정책
    -0.06
    na
    -0.06
     offsetX
    -0.06
    POSITIVE LOGITS
    存档备份
    0.08
    抽
    0.06
     Json
    0.06
     приготов
    0.06
     Aer
    0.06
    BuilderFactory
    0.05
    arParams
    0.05
     corp
    0.05
    Measured
    0.05
    []>
    0.05
    Act Density 0.197%

    No Known Activations