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

    Neuronpedia

    INDEX
    Explanations

    Dialogue/script actions

    np_max-act · gemini-2.0-flash

    roleplay-style stage directions and nonverbal action/emotion cues, especially those enclosed in asterisks or parentheses within dialogue.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    _DLL
    -0.06
    NotAllowed
    -0.06
    -bar
    -0.06
     kW
    -0.05
    :@"
    -0.05
    @RequestMapping
    -0.05
     getSystemService
    -0.05
     Saul
    -0.05
    muştur
    -0.05
     unle
    -0.05
    POSITIVE LOGITS
     setName
    0.07
     форми
    0.07
     upd
    0.07
    andidate
    0.07
    uencia
    0.07
    этому
    0.07
     hob
    0.06
    flate
    0.06
     homophobic
    0.06
    مود
    0.06
    Act Density 0.009%

    No Known Activations