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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the token “user,” i.e. when the text refers to the user in the conversation header.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    #######
    -0.07
     tedavi
    -0.06
     жод
    -0.06
    icie
    -0.06
     paní
    -0.06
     terms
    -0.06
     Wire
    -0.06
    Loading
    -0.06
     realiza
    -0.06
    _sent
    -0.06
    POSITIVE LOGITS
    -media
    0.07
    :url
    0.06
     planned
    0.06
     shuts
    0.06
    umo
    0.06
     diversity
    0.06
     legis
    0.06
    ли
    0.06
     Gaming
    0.06
    GestureRecognizer
    0.06
    Act Density 0.002%

    No Known Activations