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

    Neuronpedia

    INDEX
    Explanations

    image processing and vision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺘ
    0.69
    larımız
    0.65
    ের
    0.65
    ओं
    0.64
     ی
    0.61
    ید
    0.61
     lịch
    0.61
     چین
    0.59
    ların
    0.57
     بیش
    0.57
    POSITIVE LOGITS
     Related
    0.61
     was
    0.60
    同
    0.59
     Sense
    0.59
     has
    0.55
    ისა
    0.54
    ?
    0.54
     Developer
    0.52
     by
    0.52
    }}(
    0.52
    Act Density 0.024%

    No Known Activations