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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash

    This neuron responds to informal self-referential language—casual first-person pronouns and filler words (e.g. “I,” “just,” “another,” “guy”) that signal a conversational, colloquial tone.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BTTag
    -0.07
    Iran
    -0.07
     offenses
    -0.07
    	onChange
    -0.07
    .ArgumentParser
    -0.07
     workplaces
    -0.06
    Pages
    -0.06
     repeated
    -0.06
     очист
    -0.06
    letion
    -0.06
    POSITIVE LOGITS
    FXML
    0.07
    PEAR
    0.07
    ，以及
    0.06
    zens
    0.06
     gaz
    0.06
    CKET
    0.06
     rámci
    0.06
     Caucas
    0.06
    (credentials
    0.06
    �
    0.06
    Act Density 0.075%

    No Known Activations