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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sym
    -0.07
     ascii
    -0.07
    察
    -0.06
     dataset
    -0.06
    乐
    -0.06
    want
    -0.06
     emotion
    -0.06
    ича
    -0.06
     MPU
    -0.06
     fakt
    -0.06
    POSITIVE LOGITS
    нул
    0.07
    울
    0.06
    _checks
    0.06
    �
    0.06
    ्रध
    0.06
     passphrase
    0.06
    _gap
    0.06
    擦
    0.06
     Şampiyon
    0.06
    '%
    0.05
    Act Density 0.009%

    No Known Activations