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

    Neuronpedia

    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash

    references to “voice,” including vocal narration, assistant/command contexts, “voice of …” constructions, and devices or features involving recorded or spoken audio.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     krb
    -0.07
    打败
    -0.07
    _calibration
    -0.07
     この
    -0.07
    ไหม
    -0.07
    こん
    -0.07
    Factor
    -0.07
     coupon
    -0.07
    adoo
    -0.06
    aul
    -0.06
    POSITIVE LOGITS
     ręk
    0.07
     voice
    0.07
     ivory
    0.07
    声音
    0.07
    ɧ
    0.07
    anguage
    0.07
     voiced
    0.06
    печат
    0.06
     voices
    0.06
    偉
    0.06
    Act Density 0.014%

    No Known Activations