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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offender
    -0.08
    ，据
    -0.08
     nejen
    -0.07
     legisl
    -0.07
    ，被
    -0.07
     Blake
    -0.07
     routines
    -0.07
     nabíd
    -0.07
     protocolo
    -0.07
     handing
    -0.07
    POSITIVE LOGITS
     Betrag
    0.08
     رسمي
    0.08
    cent
    0.08
     Please
    0.08
    Pain
    0.07
     숫
    0.07
     عدد
    0.07
     الحساب
    0.07
     �
    0.07
     Цент
    0.07
    Act Density 0.021%

    No Known Activations