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

    Neuronpedia

    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash

    The neuron flags numeric literal tokens—especially floating-point numbers—wherever they appear in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Zeus
    -0.07
    _GROUP
    -0.07
     booze
    -0.07
     дорог
    -0.06
    |M
    -0.06
     Strap
    -0.06
     PLUS
    -0.06
    aban
    -0.06
     sins
    -0.06
    strap
    -0.06
    POSITIVE LOGITS
     askeri
    0.07
     هو
    0.06
    -wage
    0.06
    ैं,
    0.06
    ài
    0.06
    queryString
    0.06
    interested
    0.06
     capitalist
    0.06
    tensorflow
    0.06
    _INTERNAL
    0.06
    Act Density 0.034%

    No Known Activations