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

    Neuronpedia

    INDEX
    Explanations

    Mathematical calculations

    np_max-act · gemini-2.0-flash

    This neuron activates for numeric tokens (digits, numeric constants, and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sum
    -0.07
    CUS
    -0.07
    $post
    -0.07
    RESET
    -0.06
    _pres
    -0.06
     Pos
    -0.06
     ais
    -0.06
     warning
    -0.06
    uce
    -0.06
     Maker
    -0.06
    POSITIVE LOGITS
    주소
    0.07
     víde
    0.07
     Společ
    0.07
    üyle
    0.06
    typeparam
    0.06
    <Service
    0.06
    /meta
    0.06
    caler
    0.06
     ########.
    0.06
     pageInfo
    0.06
    Act Density 0.010%

    No Known Activations