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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects numeric quantities expressed with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Peoples
    -0.06
    amiliar
    -0.06
    OSP
    -0.05
    -level
    -0.05
    Fa
    -0.05
    raft
    -0.05
    |int
    -0.05
    ouncil
    -0.05
     анг
    -0.05
    특별
    -0.05
    POSITIVE LOGITS
     حداقل
    0.07
     xhr
    0.07
     goalie
    0.07
    _GUID
    0.07
     transpose
    0.07
     …↵
    0.07
     HttpResponseMessage
    0.06
    ोप
    0.06
    ैं।↵
    0.06
     nisi
    0.06
    Act Density 0.016%

    No Known Activations