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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash

    setups of user-posed puzzles or quantitative word problems, especially scenario descriptions with numbers that culminate in a question asking what happened or how many.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Coverage
    -0.07
    _EQUALS
    -0.07
    .delivery
    -0.07
    StreamReader
    -0.06
    Jon
    -0.06
     Objects
    -0.06
    оне
    -0.06
    _SELECTOR
    -0.06
    ummies
    -0.06
     Tubes
    -0.06
    POSITIVE LOGITS
     dentist
    0.07
     })),↵
    0.06
    										↵
    0.06
     क
    0.06
    ]}↵
    0.06
    ประสบ
    0.06
    indows
    0.06
     přist
    0.06
    НЯ
    0.06
     uranium
    0.06
    Act Density 0.158%

    No Known Activations