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

    Neuronpedia

    INDEX
    Explanations

    Hebrew question start words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Asimismo
    0.43
     denominada
    0.35
     භාවිත
    0.34
     asimismo
    0.33
     véritables
    0.33
     terdapat
    0.33
    UpdateChoice
    0.33
     floribus
    0.32
    ówczas
    0.31
     bulunmaktadır
    0.31
    POSITIVE LOGITS
     איך
    0.44
     그냥
    0.43
     கொஞ்சம்
    0.39
     żeby
    0.39
     خیلی
    0.38
     একটা
    0.38
     trochę
    0.38
     צריך
    0.37
     совсем
    0.37
     אבל
    0.36
    Act Density 0.001%

    No Known Activations