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

    Neuronpedia

    INDEX
    Explanations

    caused

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “caused” (as in the boilerplate liability phrase “however caused …”) in software license disclaimers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     نسبت
    -0.07
    thon
    -0.06
    Message
    -0.06
    .IsNullOrEmpty
    -0.06
     Παρα
    -0.06
     Поп
    -0.06
    _notifications
    -0.06
    fire
    -0.06
     بر
    -0.06
    _ctr
    -0.06
    POSITIVE LOGITS
     CAUSED
    0.08
     edil
    0.07
    rellas
    0.07
     seçim
    0.07
     кіль
    0.07
    Xã
    0.07
     되었
    0.07
     Beş
    0.06
    aliyet
    0.06
     jt
    0.06
    Act Density 0.000%

    No Known Activations