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

    Neuronpedia

    INDEX
    Explanations

    generating interactive oriented content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ніж
    0.45
     شدن
    0.45
     کردن
    0.43
     하지만
    0.42
     한
    0.42
    라면
    0.41
    ammation
    0.41
     해도
    0.40
     було
    0.39
     جایی
    0.39
    POSITIVE LOGITS
     internacionales
    0.59
     basadas
    0.50
     globales
    0.49
     occidental
    0.49
     basados
    0.48
     racionais
    0.48
     especiales
    0.47
    enciales
    0.46
     profesionales
    0.46
    mensaje
    0.45
    Act Density 0.067%

    No Known Activations