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

    Neuronpedia

    INDEX
    Explanations

    =============

    np_max-act · gemini-2.0-flash

    the presence of long runs of repeated “=” characters (section‐divider lines) in code comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .d
    -0.08
    	while
    -0.07
     numbering
    -0.07
    ustos
    -0.07
    ickness
    -0.06
    Avoid
    -0.06
    Parser
    -0.06
    進
    -0.06
     uploaded
    -0.06
    ／↵
    -0.06
    POSITIVE LOGITS
    _softc
    0.07
    =============
    0.07
     MISS
    0.07
     conversions
    0.07
    race
    0.07
     dinh
    0.06
    ................
    0.06
     ctrl
    0.06
     structs
    0.06
     umožňuje
    0.06
    Act Density 0.001%

    No Known Activations