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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric date/time tokens—especially years in document metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    án
    -0.06
    منت
    -0.06
    Custom
    -0.06
     Σχ
    -0.06
    Room
    -0.06
     incididunt
    -0.06
    uminum
    -0.06
    Thursday
    -0.06
    .getStatus
    -0.06
    َى
    -0.06
    POSITIVE LOGITS
     тр
    0.08
     专
    0.07
     coleg
    0.06
    -title
    0.06
    -destruct
    0.06
     decline
    0.06
     Bracket
    0.06
    OBJECT
    0.06
     CHtml
    0.06
     сам
    0.06
    Act Density 0.016%

    No Known Activations