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

    Neuronpedia

    INDEX
    Explanations

    information and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pří
    0.55
     прове
    0.53
    leyici
    0.50
     gini
    0.48
    OR
    0.46
     legible
    0.46
     posibil
    0.46
     do
    0.46
     Архиви
    0.45
     potest
    0.45
    POSITIVE LOGITS
    ع
    0.45
    ad
    0.43
    বীর
    0.43
    mma
    0.41
     Veterans
    0.41
    acey
    0.41
    blogger
    0.41
    bathing
    0.41
    omm
    0.40
    usa
    0.40
    Act Density 0.001%

    No Known Activations