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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Using
    0.46
     Pain
    0.46
     Through
    0.45
     Wound
    0.43
     Implicit
    0.43
     The
    0.43
     Xcode
    0.42
    ithmet
    0.41
    ตาม
    0.41
    The
    0.41
    POSITIVE LOGITS
    anskje
    0.52
     tiež
    0.50
    也會
    0.49
    بيرة
    0.49
    本当に
    0.48
     mantener
    0.48
     একদম
    0.48
    內容
    0.47
     ristorante
    0.46
     gimana
    0.46
    Act Density 0.025%

    No Known Activations