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

    Neuronpedia

    INDEX
    Explanations

    ixlib= url parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    szak
    0.39
    ăţ
    0.39
    ුණු
    0.38
     পরিত্র
    0.38
     manualmente
    0.38
    梭
    0.37
     pesquisas
    0.37
    తం
    0.36
     Petr
    0.36
    탔
    0.36
    POSITIVE LOGITS
    ริ
    0.39
     الگ
    0.39
     Rhodes
    0.37
    yaj
    0.37
    рты
    0.37
    oing
    0.36
     Swinging
    0.36
     пока
    0.36
     relocating
    0.36
     قرار
    0.35
    Act Density 0.000%

    No Known Activations