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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีต
    -0.07
     verilen
    -0.07
     negotiation
    -0.07
     urllib
    -0.07
    Severity
    -0.07
    刻
    -0.07
    潜
    -0.07
    ovenant
    -0.06
    _cam
    -0.06
    _latest
    -0.06
    POSITIVE LOGITS
    =&
    0.07
    .,↵
    0.06
    ....↵↵
    0.06
    !--
    0.06
    .program
    0.06
    ;';↵
    0.06
     nhẹ
    0.06
    ...↵
    0.06
     مفهوم
    0.06
    !).↵↵
    0.06
    Act Density 0.070%

    No Known Activations