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

    Neuronpedia

    INDEX
    Explanations

    comparative tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    čk
    0.78
    粆
    0.73
     آئی
    0.73
     চীনা
    0.70
     calificaciones
    0.70
     ограниче
    0.68
     namam
    0.68
     limitaciones
    0.68
    ertos
    0.68
    Comments
    0.67
    POSITIVE LOGITS
     bcrypt
    0.74
     paro
    0.71
     Einstellung
    0.70
    AtIndexPath
    0.68
    방
    0.67
     happening
    0.65
     occurs
    0.63
     stack
    0.63
     parity
    0.62
    肯
    0.61
    Act Density 0.032%

    No Known Activations