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

    Neuronpedia

    INDEX
    Explanations

    actions or future states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     và
    0.49
     एवं
    0.47
     и
    0.44
     comparação
    0.43
     وأ
    0.43
     sast
    0.42
     आणि
    0.42
    及
    0.42
     এবং
    0.41
     mesmo
    0.39
    POSITIVE LOGITS
     ਕਰਨ
    0.49
    ต้อง
    0.45
    pped
    0.45
    pples
    0.45
     toppings
    0.45
     треба
    0.43
    pping
    0.43
     normals
    0.43
    TintMode
    0.41
     നടത്ത
    0.41
    Act Density 0.015%

    No Known Activations