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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron primarily detects floating‐point numeric literals (decimal constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /book
    -0.06
    leased
    -0.06
     Ara
    -0.06
    otic
    -0.06
    CHASE
    -0.06
    mitters
    -0.06
    Introduced
    -0.06
    thetic
    -0.06
    VICES
    -0.06
     Amend
    -0.06
    POSITIVE LOGITS
     člověka
    0.07
    ––
    0.06
    альная
    0.06
    xab
    0.06
    죽
    0.06
    .Deserialize
    0.06
    ậu
    0.06
    _mi
    0.06
     увели
    0.06
    _retry
    0.06
    Act Density 0.002%

    No Known Activations