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

    Neuronpedia

    INDEX
    Explanations

    Various topics

    np_max-act · gemini-2.0-flash

    topic-bearing proper nouns and domain-specific nouns (entities, institutions, locations, roles) indicating the subject of the text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    *****↵
    -0.07
    izio
    -0.07
     Blades
    -0.07
     reflects
    -0.06
    jišť
    -0.06
     pearl
    -0.06
    ív
    -0.06
     vaginal
    -0.06
     �
    -0.06
    ừa
    -0.06
    POSITIVE LOGITS
    toLocale
    0.06
     swal
    0.06
    _minute
    0.06
    NewItem
    0.06
     EEPROM
    0.06
     koruy
    0.06
    -paced
    0.06
    (deck
    0.06
    (worker
    0.06
     Dön
    0.05
    Act Density 0.368%

    No Known Activations