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

    Neuronpedia

    INDEX
    Explanations

    watch

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words and word forms that refer to viewing or watching media (e.g. “watch,” “viewers,” “viewership”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    issor
    -0.06
    PathVariable
    -0.06
    PostalCodes
    -0.06
     telefono
    -0.06
     ceny
    -0.06
    ’a
    -0.06
    Merge
    -0.06
     evaluated
    -0.06
     vay
    -0.06
    wagon
    -0.06
    POSITIVE LOGITS
     watching
    0.07
    $view
    0.06
    PREC
    0.06
     вб
    0.06
     witnessed
    0.06
    =default
    0.06
    _SMALL
    0.06
     इसक
    0.06
    taient
    0.06
    PressEvent
    0.06
    Act Density 0.040%

    No Known Activations