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

    Neuronpedia

    INDEX
    Explanations

    key protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    숙
    0.38
    ს
    0.38
     ശ
    0.38
    পাতি
    0.38
    しさ
    0.37
    ಕ್ಕಾಗಿ
    0.36
    ན
    0.35
     ಎ
    0.35
     pave
    0.34
    面積
    0.34
    POSITIVE LOGITS
    驰
    0.43
     Metab
    0.39
     evangel
    0.38
    ➰
    0.38
     ریا
    0.36
    associations
    0.36
    ంక
    0.35
    🔵
    0.35
    尚
    0.34
    ступа
    0.34
    Act Density 0.000%

    No Known Activations