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

    Neuronpedia

    INDEX
    Explanations

    main entry point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.55
    േന
    0.46
    injlim
    0.46
     combatt
    0.45
    ฯ
    0.45
    َص
    0.44
     ಸಮಯ
    0.44
     тощо
    0.44
    ፡
    0.44
    ത്യ
    0.43
    POSITIVE LOGITS
    ن
    0.49
     Peek
    0.43
    /
    0.43
     "./
    0.42
     üret
    0.42
     t
    0.41
    购买
    0.41
     altas
    0.41
     bk
    0.41
     prakt
    0.41
    Act Density 0.001%

    No Known Activations