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

    Neuronpedia

    INDEX
    Explanations

    personal narratives

    np_max-act · gemini-2.0-flash

    The neuron detects personal-voice cues—especially first- and second-person pronouns and related tokens that signal subjective or opinionated language (e.g. “I,” “you,” “my,” “we”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    058
    -0.07
     montage
    -0.06
    dm
    -0.06
     ю
    -0.06
    ิวเตอร
    -0.06
    .STATUS
    -0.06
    804
    -0.06
    comput
    -0.06
    تب
    -0.06
    061
    -0.06
    POSITIVE LOGITS
    _star
    0.06
    (pages
    0.06
     трь
    0.06
    illiseconds
    0.06
    Excellent
    0.06
     People
    0.06
    getDb
    0.06
    ixo
    0.06
    ……………………
    0.06
    .getElementsByClassName
    0.06
    Act Density 0.270%

    No Known Activations