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

    Neuronpedia

    INDEX
    Explanations

    practice questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     läbi
    0.53
    Polynomial
    0.49
    ᙱ
    0.49
    ার্জি
    0.47
     procédés
    0.46
     فِي
    0.46
    ൪
    0.46
    Boxing
    0.45
     denen
    0.45
    Servo
    0.45
    POSITIVE LOGITS
    ili
    0.46
    anya
    0.45
    ation
    0.45
     হওয়ায়
    0.44
     ambigu
    0.43
     уйный
    0.43
     قاسمی
    0.42
    ianza
    0.41
     inadvertently
    0.41
     बढ़ाता
    0.41
    Act Density 0.005%

    No Known Activations