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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and fires on nothing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     علی
    -0.07
     term
    -0.07
     Пр
    -0.06
    .Linear
    -0.06
    oğu
    -0.06
     Coul
    -0.06
     نظری
    -0.06
    _pkt
    -0.06
    yer
    -0.06
    узы
    -0.06
    POSITIVE LOGITS
    らしい
    0.07
     signatures
    0.06
     assessed
    0.06
    .cwd
    0.06
     lugar
    0.06
     обов
    0.06
     نحوه
    0.06
     Wizard
    0.06
    าจารย
    0.06
     Invisible
    0.06
    Act Density 0.056%

    No Known Activations