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

    Neuronpedia

    INDEX
    Explanations

    solely, purely, only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     например
    0.49
    бо
    0.47
    ж
    0.46
     있다면
    0.45
     Например
    0.44
     मदद
    0.44
    например
    0.44
     이벤트
    0.44
    ซ์
    0.43
    е
    0.43
    POSITIVE LOGITS
     únicamente
    0.45
     purely
    0.44
     non
    0.43
     uniquement
    0.42
     only
    0.41
     somente
    0.41
     solely
    0.41
     endast
    0.39
     reminis
    0.39
     Spartans
    0.39
    Act Density 0.002%

    No Known Activations