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

    Neuronpedia

    INDEX
    Explanations

    matrix math code

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (e.g. decimal values in code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     případech
    -0.07
     notas
    -0.06
    (TRUE
    -0.06
    [rand
    -0.06
    _texts
    -0.06
    ょう
    -0.06
     reasonably
    -0.06
    řejmě
    -0.06
    .Cond
    -0.06
    ')}}">↵
    -0.06
    POSITIVE LOGITS
    ayload
    0.07
    สาร
    0.06
    fdf
    0.06
    ikip
    0.06
     Fishing
    0.06
     shard
    0.06
    िप
    0.06
     Cork
    0.06
    acies
    0.06
     đàn
    0.06
    Act Density 0.003%

    No Known Activations