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

    Neuronpedia

    INDEX
    Explanations

    lists of categories or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    চ্ছেদ
    0.47
     -!
    0.44
    ain
    0.42
     risking
    0.41
     _|
    0.41
    imh
    0.40
    hits
    0.40
    !”.
    0.40
    !*\
    0.40
     reloading
    0.40
    POSITIVE LOGITS
     Disability
    0.47
     permettre
    0.47
     मिश्र
    0.44
    品种
    0.44
    对于
    0.44
     уровня
    0.43
     padrões
    0.42
    Tous
    0.41
    рованием
    0.41
    确定
    0.40
    Act Density 0.008%

    No Known Activations