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

    Neuronpedia

    INDEX
    Explanations

    Code/math snippets

    np_max-act · gemini-2.0-flash

    This neuron detects decimal number tokens (floating‐point numerals with fractional parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sth
    -0.07
     �
    -0.07
     authentication
    -0.06
     channels
    -0.06
     sağlayan
    -0.06
    pixels
    -0.06
    identify
    -0.06
    .Inv
    -0.06
    by
    -0.06
     сообщ
    -0.06
    POSITIVE LOGITS
     موسیقی
    0.06
     grantResults
    0.06
     complic
    0.06
     Jacksonville
    0.06
    ’à
    0.06
     yeme
    0.06
    _maps
    0.06
    уванні
    0.06
    agini
    0.06
    732
    0.06
    Act Density 0.034%

    No Known Activations