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

    Neuronpedia

    INDEX
    Explanations

    thought experiment and exercises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     అందించ
    0.38
     hairline
    0.38
     oversee
    0.37
     dashing
    0.37
    قق
    0.36
    飘
    0.36
    TDto
    0.35
     hust
    0.34
     cupr
    0.34
     victorias
    0.34
    POSITIVE LOGITS
     exercises
    2.00
     exercise
    1.82
    exercises
    1.79
     упраж
    1.77
     Exercises
    1.72
    Exercises
    1.72
    exercise
    1.67
     exercícios
    1.64
     exercices
    1.63
     exercice
    1.61
    Act Density 0.033%

    No Known Activations