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

    Neuronpedia

    INDEX
    Explanations

    numbers and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     위치
    0.38
     канал
    0.38
     Voici
    0.38
     快
    0.38
     Ud
    0.37
    条款
    0.37
    DS
    0.36
     جانتے
    0.36
    到位
    0.36
     relevant
    0.35
    POSITIVE LOGITS
    änk
    0.42
     unrelenting
    0.41
    englisch
    0.41
     diaphr
    0.40
     ank
    0.39
     fii
    0.39
    asthenia
    0.38
     capric
    0.38
    né
    0.38
     append
    0.38
    Act Density 0.000%

    No Known Activations