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

    Neuronpedia

    INDEX
    Explanations

    state laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     એપ
    0.52
     doméstica
    0.50
    èvement
    0.49
    व्यापी
    0.47
     Rússia
    0.47
     عصر
    0.47
    어요
    0.46
    フジ
    0.46
    앱
    0.46
    鄀
    0.46
    POSITIVE LOGITS
     bleibt
    0.42
    趔
    0.42
    端的
    0.39
    (
    0.38
    тился
    0.37
    I
    0.36
     disconnection
    0.36
    ਆਂ
    0.36
     Bein
    0.35
    式的
    0.35
    Act Density 0.006%

    No Known Activations