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

    Neuronpedia

    INDEX
    Explanations

    every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mobilized
    0.70
     நடந்த
    0.69
     stanje
    0.65
     wheels
    0.64
    لفة
    0.64
     colonization
    0.64
    spiracy
    0.64
    женные
    0.63
     pilgrims
    0.63
     akci
    0.63
    POSITIVE LOGITS
    how
    0.65
    रस
    0.65
    сия
    0.64
    every
    0.61
    0.61
    más
    0.60
     ways
    0.58
    이지
    0.58
    วา
    0.57
    𝑆
    0.57
    Act Density 0.030%

    No Known Activations