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

    Neuronpedia

    INDEX
    Explanations

    goods

    np_max-act · gemini-2.0-flash

    the literal token “GOODS,” as in “substitute GOODS” in software‐license disclaimers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sede
    -0.07
     центр
    -0.07
     Cit
    -0.07
     tội
    -0.07
     commande
    -0.07
    漂
    -0.07
    emente
    -0.06
     lavoro
    -0.06
    _print
    -0.06
     Söz
    -0.06
    POSITIVE LOGITS
     GOODS
    0.11
    ./(
    0.07
    (fb
    0.06
    ?'↵↵
    0.06
     rtn
    0.06
    <_
    0.06
    .cos
    0.06
     Samples
    0.06
    belief
    0.06
    BH
    0.06
    Act Density 0.000%

    No Known Activations