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

    Neuronpedia

    INDEX
    Explanations

    font size

    np_max-act · gemini-2.0-flash

    This neuron never fires—its activations are all zero—so it isn’t detecting any particular token or pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     voice
    -0.07
    _json
    -0.07
     center
    -0.07
     records
    -0.07
    But
    -0.07
    字幕
    -0.07
     waves
    -0.06
    -ф
    -0.06
     Blood
    -0.06
    .handlers
    -0.06
    POSITIVE LOGITS
    伸
    0.07
    ρη
    0.06
    fos
    0.06
     حذف
    0.06
    resa
    0.06
     meses
    0.06
    .firstChild
    0.06
    vido
    0.06
     FormsModule
    0.06
    การส
    0.06
    Act Density 0.002%

    No Known Activations