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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Fabric
    -0.07
     Judgment
    -0.07
     seekers
    -0.07
    Pic
    -0.06
     vice
    -0.06
     готов
    -0.06
     законодав
    -0.06
    ुम
    -0.06
    DLL
    -0.06
    DA
    -0.06
    POSITIVE LOGITS
     unin
    0.07
    cılar
    0.06
     Hence
    0.06
    ThanOrEqualTo
    0.06
     incomplete
    0.06
    ератор
    0.06
     apro
    0.06
     campo
    0.06
                      ↵
    0.06
     운영
    0.06
    Act Density 0.015%

    No Known Activations