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

    Neuronpedia

    INDEX
    Explanations

    other languages, synonyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perpetrator
    0.44
    اريخ
    0.43
    hormat
    0.40
     laatste
    0.40
    宇宙
    0.39
     oppress
    0.38
     posl
    0.38
     Bauch
    0.38
    etva
    0.38
     in
    0.38
    POSITIVE LOGITS
     perfección
    0.46
     chopping
    0.42
     demás
    0.42
    خته
    0.42
    determining
    0.41
     άλλα
    0.41
    駈
    0.41
    autres
    0.41
     سایر
    0.41
     अन्य
    0.39
    Act Density 0.002%

    No Known Activations