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

    Neuronpedia

    INDEX
    Explanations

    blocking malicious IPs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ii
    0.47
     Twelfth
    0.45
    িনার
    0.43
     সাপ
    0.41
     Simplify
    0.41
    airline
    0.41
     নির্দিষ্ট
    0.40
    ClientSize
    0.39
    鰍
    0.39
    iculata
    0.39
    POSITIVE LOGITS
    м
    0.54
    راحة
    0.49
     violation
    0.45
     chauffage
    0.45
    的地
    0.44
    сто
    0.43
     arterial
    0.43
     großer
    0.43
    elijk
    0.43
    س
    0.43
    Act Density 0.003%

    No Known Activations