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 selectively activates on numeric date tokens (years) in filmography or career lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    تص
    -0.07
    เคร
    -0.06
    _ts
    -0.06
    .findIndex
    -0.06
    指导
    -0.06
     зер
    -0.06
    onedDateTime
    -0.06
     elapsedTime
    -0.06
    .finish
    -0.06
     เคร
    -0.06
    POSITIVE LOGITS
    [word
    0.07
    gener
    0.07
    202
    0.06
    Sau
    0.06
    /**
    0.06
     visionary
    0.06
    201
    0.06
    choice
    0.06
    predicted
    0.06
    895
    0.06
    Act Density 0.012%

    No Known Activations