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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash

    This neuron appears to be inactive—it does not reliably activate on any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    fact
    -0.07
    seven
    -0.06
    eggies
    -0.06
    ">↵↵↵
    -0.06
    batch
    -0.06
    柴
    -0.06
    027
    -0.06
     fifth
    -0.06
    Getty
    -0.06
     걸
    -0.06
    POSITIVE LOGITS
    Workspace
    0.07
    ('"
    0.07
    ,-
    0.06
     ROT
    0.06
    -shirts
    0.06
    █
    0.06
     Ô
    0.06
     Ö
    0.06
    ˆ
    0.06
    _Parameter
    0.06
    Act Density 0.002%

    No Known Activations