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

    Neuronpedia

    INDEX
    Explanations

    impeccable service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Munt
    0.40
     برش
    0.39
     비밀
    0.38
     حصول
    0.37
     Министерства
    0.37
     Mt
    0.37
     ministère
    0.36
     فانه
    0.35
     corruption
    0.35
     جات
    0.34
    POSITIVE LOGITS
    ✨
    0.43
    biggest
    0.40
     biggest
    0.39
     SLO
    0.39
    slo
    0.39
    можно
    0.39
    Filled
    0.39
    enhuma
    0.39
    easy
    0.38
    Zombie
    0.38
    Act Density 0.000%

    No Known Activations