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

    Neuronpedia

    INDEX
    Explanations

    GPT-3.5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bend
    0.46
     पाली
    0.45
     bending
    0.41
    Bened
    0.41
     bends
    0.40
     Bend
    0.40
     Bent
    0.39
     واللي
    0.38
     Benedict
    0.38
    Bend
    0.38
    POSITIVE LOGITS
    silk
    0.38
    ネイ
    0.36
    倉
    0.35
     Sah
    0.35
    Pe
    0.34
    Sah
    0.34
     Herrmann
    0.34
     silks
    0.34
    orni
    0.34
    GSM
    0.34
    Act Density 0.008%

    No Known Activations