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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    408
    -0.07
    蒂
    -0.07
    212
    -0.07
     trucks
    -0.07
     venue
    -0.07
     MES
    -0.07
    87
    -0.06
     Pikachu
    -0.06
    396
    -0.06
     rigs
    -0.06
    POSITIVE LOGITS
    <?>
    0.07
     doesn
    0.06
    _CANNOT
    0.06
    .sample
    0.06
     kidn
    0.06
    !)↵↵
    0.06
    []):
    0.06
    Released
    0.06
     persisted
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
    Act Density 0.014%

    No Known Activations