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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Configure
    -0.08
    .Value
    -0.08
    (nums
    -0.08
     организм
    -0.08
     pareil
    -0.08
     quinze
    -0.08
     infantry
    -0.08
    [^
    -0.08
     relata
    -0.08
    (Configuration
    -0.08
    POSITIVE LOGITS
     specialties
    0.10
    特殊
    0.09
    _special
    0.09
     especiales
    0.09
    国外
    0.09
     unconventional
    0.09
     special
    0.08
    Unexpected
    0.08
     specialty
    0.08
     Unexpected
    0.08
    Act Density 0.229%

    No Known Activations