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

    Neuronpedia

    INDEX
    Explanations

    system calls

    np_max-act · gemini-2.0-flash

    This neuron primarily responds to floating-point numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (data
    -0.07
    ("--------------------------------
    -0.06
    lédl
    -0.06
     NSLocalizedString
    -0.06
     христи
    -0.06
     Quý
    -0.06
    .PI
    -0.06
    (Tile
    -0.06
    _APPEND
    -0.06
    .INPUT
    -0.06
    POSITIVE LOGITS
    ços
    0.07
    冠
    0.07
    itus
    0.07
    elo
    0.06
     dentro
    0.06
    coordinate
    0.06
    rostřed
    0.06
    ngthen
    0.06
    unteers
    0.06
    rido
    0.06
    Act Density 0.003%

    No Known Activations