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

    Neuronpedia

    INDEX
    Explanations

    i do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pozn
    0.40
     meilleures
    0.39
    apr
    0.38
     விழா
    0.37
    ቀም
    0.36
    avil
    0.36
    Rounded
    0.36
    timber
    0.35
     विभागों
    0.35
     আট
    0.35
    POSITIVE LOGITS
     скульп
    0.38
    нет
    0.38
     нет
    0.38
    rils
    0.37
    cych
    0.37
    rital
    0.36
    هان
    0.36
     интенсив
    0.36
     ہاتھوں
    0.36
    喚
    0.35
    Act Density 0.000%

    No Known Activations