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

    Neuronpedia

    INDEX
    Explanations

    foreign language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whopping
    0.49
     hamburgers
    0.47
    遺跡
    0.45
    ارك
    0.44
    宽度
    0.43
     amperes
    0.43
     promises
    0.43
     ক্ষত্র
    0.42
     Welles
    0.42
     Textile
    0.42
    POSITIVE LOGITS
    Equipo
    0.52
     servicios
    0.47
     equipo
    0.47
    EQU
    0.47
     servizi
    0.47
    zeige
    0.45
     στοι
    0.45
     Equipo
    0.44
     गुरु
    0.44
     criterio
    0.44
    Act Density 0.018%

    No Known Activations