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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash

    The neuron flags tokens representing numbers or numeric values (e.g. digits, multi-digit numbers, and decimal figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     providing
    -0.06
    舞
    -0.06
    (box
    -0.06
    された
    -0.06
     provided
    -0.06
     Premiere
    -0.06
    Table
    -0.06
    edges
    -0.06
     Explore
    -0.06
     rank
    -0.06
    POSITIVE LOGITS
    ัดการ
    0.07
    DY
    0.07
    @author
    0.07
    *Math
    0.07
    �ん
    0.07
    sequ
    0.06
    BUTTONDOWN
    0.06
    _poll
    0.06
    ерж
    0.06
    eton
    0.06
    Act Density 0.009%

    No Known Activations