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

    Neuronpedia

    INDEX
    Explanations

    code elements and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    етки
    0.44
     ACLU
    0.44
     अधिकतम
    0.44
     shotgun
    0.41
     encompassed
    0.41
     আদালতে
    0.41
     swiftly
    0.40
    етка
    0.40
     attorney
    0.40
    emakers
    0.40
    POSITIVE LOGITS
    Painting
    0.48
     Haber
    0.43
    System
    0.40
    าศ
    0.39
     Gog
    0.39
    烹
    0.39
    Quan
    0.38
     gö
    0.38
     זו
    0.38
     Gober
    0.38
    Act Density 0.059%

    No Known Activations