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

    Neuronpedia

    INDEX
    Explanations

    utility and benefit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ไม่ใช่
    0.45
     normalement
    0.42
     विशेषताएं
    0.41
     स्वाभाविक
    0.40
    chanics
    0.36
    toBe
    0.36
    Aber
    0.36
    맣
    0.36
    シェ
    0.35
    㢳
    0.35
    POSITIVE LOGITS
     meaningful
    0.85
     useful
    0.84
     helpful
    0.84
     meaningfully
    0.80
     utile
    0.78
     도움이
    0.74
     útil
    0.73
     فائدہ
    0.71
     productive
    0.70
     berguna
    0.70
    Act Density 0.015%

    No Known Activations