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

    Neuronpedia

    INDEX
    Explanations

    docs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     радян
    -0.06
     gave
    -0.06
    -cr
    -0.06
     improbable
    -0.06
     ﾞ
    -0.06
     パ
    -0.06
    lie
    -0.06
     fer
    -0.06
     Tou
    -0.06
     attractive
    -0.06
    POSITIVE LOGITS
    /docs
    0.09
    docs
    0.08
     Miss
    0.08
     documentation
    0.08
     warning
    0.07
     Plus
    0.07
    ILLS
    0.07
    isci
    0.07
    inheritDoc
    0.07
    (dis
    0.06
    Act Density 0.003%

    No Known Activations