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

    Neuronpedia

    INDEX
    Explanations

    graffiti

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on descriptive, attention-grabbing content words (adjectives and nouns) that highlight unique or noteworthy attributes or actions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ant
    -0.07
     Witch
    -0.07
    ServerError
    -0.06
    _ticket
    -0.06
    Att
    -0.06
    数据
    -0.06
     segment
    -0.06
     girlfriends
    -0.06
     ته
    -0.06
     mirror
    -0.06
    POSITIVE LOGITS
    ****************************************
    0.08
     rand
    0.07
     pyplot
    0.07
    sip
    0.06
    ADED
    0.06
    ivil
    0.06
    @FXML
    0.06
    ่อไป
    0.06
    indow
    0.06
    ................................
    0.06
    Act Density 1.387%

    No Known Activations