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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of books or book excerpts (e.g., tokens like “book,” “books,” “excerpt,” “chapter”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fertilizer
    -0.06
    (name
    -0.06
    Status
    -0.06
    hyp
    -0.06
     tiger
    -0.06
     fungi
    -0.06
    ू
    -0.06
     جذ
    -0.06
    (foo
    -0.06
    _dict
    -0.06
    POSITIVE LOGITS
    asından
    0.07
    мом
    0.07
     aftermarket
    0.06
     lenght
    0.06
     unemployed
    0.06
    arella
    0.06
    RESULT
    0.06
     gritty
    0.06
     redistrib
    0.06
    /frontend
    0.06
    Act Density 0.109%

    No Known Activations