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

    Neuronpedia

    INDEX
    Explanations

    code/XML

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric literals—especially floating-point numbers—in code or data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    acao
    -0.07
    	cm
    -0.07
     barely
    -0.06
    _CARD
    -0.06
     گرفت
    -0.06
    严
    -0.06
     yoga
    -0.06
     '|
    -0.06
     RTVF
    -0.06
    _gr
    -0.06
    POSITIVE LOGITS
    _RING
    0.07
     profitability
    0.07
     nouve
    0.06
    uteur
    0.06
     Chung
    0.06
    ITHUB
    0.06
    .Font
    0.06
    .getLabel
    0.06
     Assurance
    0.06
    .android
    0.06
    Act Density 0.149%

    No Known Activations