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

    Neuronpedia

    INDEX
    Explanations

    databases access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naughty
    0.45
     troops
    0.42
    م
    0.41
     popularity
    0.40
     loves
    0.40
     troupes
    0.40
     ruler
    0.39
     baddies
    0.39
    انی
    0.38
     pundits
    0.37
    POSITIVE LOGITS
     трансформа
    0.44
    পদার্থ
    0.41
    btn
    0.41
     проекти
    0.40
     Букмекердик
    0.40
    ēl
    0.39
    awed
    0.39
    ungkinkan
    0.39
     кине
    0.39
    ITECT
    0.39
    Act Density 0.007%

    No Known Activations