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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash

    This neuron is selectively activating on numeric tokens (e.g. IDs, dates, counts) wherever digits appear in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     generalized
    -0.07
     기술
    -0.07
    Restore
    -0.07
     Execution
    -0.07
    .zoom
    -0.07
    �
    -0.06
     sales
    -0.06
    ах
    -0.06
    om
    -0.06
     Esk
    -0.06
    POSITIVE LOGITS
    مع
    0.07
    emailer
    0.06
    isateur
    0.06
    agram
    0.06
    blo
    0.06
    _Bl
    0.06
    reshape
    0.06
    DATES
    0.06
     облі
    0.06
     actualizar
    0.06
    Act Density 0.035%

    No Known Activations