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

    Neuronpedia

    INDEX
    Explanations

    Mr./Ms./Mx. followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পৃ
    0.74
     Rohing
    0.67
    စ္
    0.64
     мебели
    0.64
    гран
    0.63
     মনোন
    0.62
    coroutines
    0.62
    fiche
    0.62
    ূর্তি
    0.61
    蒙古
    0.61
    POSITIVE LOGITS
     LaSalle
    0.69
     WR
    0.64
     herm
    0.62
     ssize
    0.57
     Hers
    0.57
     cons
    0.54
     Her
    0.54
     asignatura
    0.53
     thereto
    0.53
     Laure
    0.53
    Act Density 0.004%

    No Known Activations