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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron flags question boundaries—i.e. the “?” at the end of a user query (and related end‐of‐turn tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lt
    -0.07
     invaders
    -0.06
     Wise
    -0.06
     fizz
    -0.06
    formats
    -0.06
    ptime
    -0.06
     tk
    -0.06
     Whilst
    -0.06
     kW
    -0.06
    .reload
    -0.06
    POSITIVE LOGITS
    reglo
    0.07
    .cgColor
    0.06
    ?↵
    0.06
    ?"↵
    0.06
    (Abstract
    0.06
    .BatchNorm
    0.06
    }()↵
    0.06
    .vstack
    0.06
     Macros
    0.06
     hại
    0.06
    Act Density 0.089%

    No Known Activations