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

    Neuronpedia

    INDEX
    Explanations

    programming code and optionals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tribute
    -0.09
     indruk
    -0.08
    ied
    -0.07
    _Rem
    -0.07
     Tribute
    -0.07
     tunes
    -0.07
     dictionaries
    -0.07
    'impression
    -0.07
     الدرا
    -0.07
    姐妹
    -0.07
    POSITIVE LOGITS
     Nullable
    0.11
     nullable
    0.11
    (nullable
    0.11
    _nullable
    0.11
    nullable
    0.11
    Nullable
    0.11
    .Nullable
    0.09
     lumen
    0.09
    .null
    0.08
    @All
    0.08
    Act Density 0.004%

    No Known Activations