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

    Neuronpedia

    INDEX
    Explanations

    whether/if

    np_max-act · gemini-2.0-flash

    the introduction of research questions or objectives (e.g., “whether,” “determine,” “investigate,” “ask”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    candidates
    -0.07
    _phr
    -0.07
    -NLS
    -0.06
    句
    -0.06
     actress
    -0.06
    438
    -0.06
     Exclusive
    -0.06
     extras
    -0.06
    REDENTIAL
    -0.06
     #
↵
    -0.06
    POSITIVE LOGITS
    edin
    0.06
     acompañ
    0.06
     associate
    0.06
     weird
    0.06
     Routine
    0.06
    (Long
    0.06
     LABEL
    0.06
    .ht
    0.06
     모두
    0.06
     therein
    0.06
    Act Density 0.065%

    No Known Activations