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

    Neuronpedia

    INDEX
    Explanations

    acknowledging the situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     King
    0.44
    ੋ
    0.43
    host
    0.40
    King
    0.39
    inst
    0.38
    zogen
    0.38
    oven
    0.38
    Bers
    0.38
    isch
    0.37
    Host
    0.37
    POSITIVE LOGITS
     появляются
    0.52
    的价格
    0.47
    า
    0.47
     требуют
    0.47
     पड़ता
    0.45
     نیز
    0.45
     produisent
    0.45
     bauen
    0.44
     ежедневно
    0.44
     нужны
    0.44
    Act Density 0.000%

    No Known Activations