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

    Neuronpedia

    INDEX
    Explanations

    watching someone or something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পুরের
    1.34
    पीड़न
    1.32
     faptul
    1.31
    क
    1.26
    基づ
    1.21
    ج
    1.21
    ിയ
    1.17
    یز
    1.17
     ficando
    1.15
    пиа
    1.13
    POSITIVE LOGITS
     helplessly
    1.72
    tower
    1.69
    ה
    1.58
    া
    1.54
    a
    1.50
    tive
    1.41
    ا
    1.38
     xét
    1.38
    jší
    1.36
    нга
    1.29
    Act Density 0.043%

    No Known Activations