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

    Neuronpedia

    INDEX
    Explanations

    often, sometimes, centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    수를
    0.52
    ם
    0.49
    هم
    0.48
    र्क
    0.47
    IS
    0.47
    Є
    0.47
    را
    0.46
    ة
    0.46
    وه
    0.45
    usu
    0.45
    POSITIVE LOGITS
     kript
    0.45
     lanyard
    0.43
     duration
    0.43
     jual
    0.42
     layar
    0.41
     фе
    0.41
     bios
    0.40
     CBD
    0.40
     सिया
    0.39
     निर्धारण
    0.39
    Act Density 0.003%

    No Known Activations