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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash

    the presence of numeric literal tokens (especially floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    peated
    -0.06
     addObserver
    -0.06
    rieb
    -0.06
     aprend
    -0.06
    GO
    -0.06
    Pink
    -0.06
    .sleep
    -0.06
    .BLL
    -0.06
    cepts
    -0.06
    peat
    -0.06
    POSITIVE LOGITS
     très
    0.07
    _ops
    0.07
    로그
    0.06
    .startActivity
    0.06
     amazon
    0.06
    Chooser
    0.06
     держави
    0.06
    рат
    0.06
    ’on
    0.06
    _ComCallableWrapper
    0.06
    Act Density 0.010%

    No Known Activations