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

    Neuronpedia

    INDEX
    Explanations

    Home Health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सैनिकों
    0.54
     melakukannya
    0.54
     ребенка
    0.50
    триму
    0.49
    extérieur
    0.49
     వెంటనే
    0.48
    producto
    0.47
    ższ
    0.47
    Ꮀ
    0.47
     opět
    0.46
    POSITIVE LOGITS
     [...]
    0.63
     (...)
    0.60
     ETFs
    0.56
     PhD
    0.55
     PPAR
    0.53
     […]
    0.52
     IELTS
    0.51
     Dissertation
    0.51
     Of
    0.50
    0.50
    Act Density 0.616%

    No Known Activations