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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    np_max-act · gemini-2.0-flash

    The neuron is activated by numeric tokens representing decimal values or floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    buz
    -0.07
    /front
    -0.07
     Yi
    -0.07
    ender
    -0.06
     pre
    -0.06
     Canucks
    -0.06
    аний
    -0.06
     bez
    -0.06
    _card
    -0.06
     actually
    -0.06
    POSITIVE LOGITS
    _HELPER
    0.07
    .GetById
    0.07
     brushed
    0.07
     Guardians
    0.07
    рав
    0.06
     の
    0.06
    _phrase
    0.06
     système
    0.06
     tehlik
    0.06
    .httpClient
    0.06
    Act Density 0.007%

    No Known Activations