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

    Neuronpedia

    INDEX
    Explanations

    feasibility, usability, accessibility issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activité
    0.51
    ifiably
    0.51
    ness
    0.48
     activity
    0.47
     actividad
    0.47
    autorité
    0.46
     cantidad
    0.46
     cantidades
    0.45
     attività
    0.45
     magnitud
    0.45
    POSITIVE LOGITS
     issues
    0.52
    issues
    0.52
     Issues
    0.47
    tests
    0.45
    -}
    0.43
    Issues
    0.42
    yyyy
    0.42
     मैट्रिक्स
    0.41
     factors
    0.41
     спи
    0.41
    Act Density 0.055%

    No Known Activations