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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giorno
    -0.07
     بالنسبة
    -0.07
    参
    -0.07
    ⵙ
    -0.07
     Dzięki
    -0.07
     Palestin
    -0.07
     residuals
    -0.07
    cesso
    -0.07
     hors
    -0.06
     fasting
    -0.06
    POSITIVE LOGITS
    =>{↵
    0.08
    幢
    0.07
     Vacation
    0.07
     Fon
    0.07
    �
    0.07
     juven
    0.07
    振
    0.07
    (Conv
    0.06
    .IntegerField
    0.06
    ;")↵
    0.06
    Act Density 0.008%

    No Known Activations