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

    Neuronpedia

    INDEX
    Explanations

    foliage and shirt context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    1.03
     назна
    1.02
    ן
    0.96
    РА
    0.94
    му
    0.91
    에는
    0.91
    ется
    0.89
    ми
    0.89
    습니다
    0.87
    FrameID
    0.86
    POSITIVE LOGITS
    free
    0.90
    त्तर
    0.87
    zul
    0.83
    zier
    0.83
    kers
    0.82
    ğı
    0.82
    hler
    0.82
    zinho
    0.82
    x
    0.82
    peg
    0.81
    Act Density 0.000%

    No Known Activations