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

    Neuronpedia

    INDEX
    Explanations

    narrative excerpts

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting subjective, evaluative language—especially positive intensifiers and adjectives (e.g. “certainly,” “excellent,” “very,” “well,” “most”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vidia
    -0.06
    许多
    -0.06
    scaling
    -0.06
    Ham
    -0.06
     免
    -0.06
     olumlu
    -0.06
    ctp
    -0.06
     mocked
    -0.06
     Callback
    -0.06
    Exam
    -0.06
    POSITIVE LOGITS
     ballo
    0.07
    unal
    0.06
    Navigation
    0.06
     HEIGHT
    0.06
     chữ
    0.06
     aes
    0.06
     Nguyen
    0.06
     administrators
    0.06
    _UNIT
    0.06
     numbering
    0.06
    Act Density 0.036%

    No Known Activations