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

    Neuronpedia

    INDEX
    Explanations

    items for objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Василь
    0.46
    ورية
    0.43
     గో
    0.43
    ংলার
    0.42
    azim
    0.42
     Tompkins
    0.42
     призна
    0.41
    платы
    0.41
    abha
    0.41
     కనిప
    0.40
    POSITIVE LOGITS
    iske
    0.49
    های
    0.48
    iskt
    0.45
    مت
    0.44
    λ
    0.44
    ռ
    0.43
     shutt
    0.43
    د
    0.43
    مس
    0.42
    물이
    0.42
    Act Density 0.000%

    No Known Activations