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

    Neuronpedia

    INDEX
    Explanations

    void

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    diğ
    -0.08
    -campus
    -0.07
    מכבי
    -0.07
    겅
    -0.07
     atte
    -0.07
     vault
    -0.07
    얘
    -0.06
     baff
    -0.06
    所以我
    -0.06
    对我
    -0.06
    POSITIVE LOGITS
    _pts
    0.07
     Invoke
    0.07
    国产
    0.07
    wrap
    0.07
    .Doc
    0.07
     Food
    0.07
    Detail
    0.07
     dial
    0.07
     Brun
    0.07
    _policy
    0.07
    Act Density 0.002%

    No Known Activations