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

    Neuronpedia

    INDEX
    Explanations

    `%%a` in or similar token

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')
    0.46
     ').
    0.42
     ')
    0.40
     oppure
    0.39
    ').
    0.38
    incott
    0.38
    ྕ
    0.37
     أت
    0.35
     或者
    0.34
     ");
    0.34
    POSITIVE LOGITS
     setIsLoading
    0.43
     hodin
    0.41
     pau
    0.39
     Üniversitesi
    0.37
     évolution
    0.36
    horas
    0.36
    ड़ियों
    0.36
     portfolios
    0.36
    [{\
    0.35
     اعمال
    0.35
    Act Density 0.001%

    No Known Activations