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

    Neuronpedia

    INDEX
    Explanations

    level up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ของการ
    0.42
     tensione
    0.42
     résultat
    0.40
     conduction
    0.40
     oxidación
    0.40
     abstinence
    0.39
     copertura
    0.39
    पर्यंत
    0.39
     réussite
    0.39
     layers
    0.38
    POSITIVE LOGITS
     lev
    0.69
     Lev
    0.66
     leveling
    0.63
    Lev
    0.61
     levelled
    0.55
     leveled
    0.52
     Lv
    0.52
    lv
    0.48
    LEV
    0.48
     LV
    0.47
    Act Density 0.007%

    No Known Activations