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

    Neuronpedia

    INDEX
    Explanations

    potential overflow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ग्रा
    0.57
     एवरी
    0.50
    SA
    0.48
     Aplikasi
    0.47
    кла
    0.47
     არს
    0.46
     Accessible
    0.46
    த்தை
    0.45
     mengakses
    0.45
    Manip
    0.45
    POSITIVE LOGITS
     ejer
    0.46
     fanc
    0.45
     kopen
    0.45
     deliberations
    0.43
     DLC
    0.42
     kiezen
    0.42
    \"]
    0.42
    كمة
    0.42
     Temper
    0.41
     diabetic
    0.41
    Act Density 0.003%

    No Known Activations