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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literal tokens (especially floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Jack
    -0.08
     aile
    -0.07
    選択
    -0.07
     grids
    -0.07
     Bedroom
    -0.07
    inges
    -0.06
    _geo
    -0.06
    Lord
    -0.06
    Flex
    -0.06
    Saved
    -0.06
    POSITIVE LOGITS
     crian
    0.07
    ...";↵
    0.06
    ้าท
    0.06
     dưới
    0.06
    .Utility
    0.06
    ...");↵
    0.06
     *)[
    0.06
     Medi
    0.06
     μην
    0.06
    ْ
    0.06
    Act Density 0.039%

    No Known Activations