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

    Neuronpedia

    INDEX
    Explanations

    defining environment, frame rate, low tensile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    思い
    0.42
     zab
    0.41
    Hide
    0.40
     Stratton
    0.39
    ନ୍
    0.38
    reib
    0.38
     reh
    0.37
    Night
    0.37
     hiding
    0.37
     Poe
    0.36
    POSITIVE LOGITS
    ظ
    0.41
    ಟ್‌
    0.39
     جوہری
    0.39
    🠀
    0.37
    并将
    0.37
    头上
    0.37
    得到的
    0.36
     الظ
    0.36
    spraak
    0.35
    并且
    0.35
    Act Density 0.125%

    No Known Activations