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

    Neuronpedia

    INDEX
    Explanations

    numbers, details, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ኔታ
    0.49
    iyor
    0.48
    vana
    0.47
     ইয়াহিয়া
    0.46
    કિસ્
    0.46
     ইয়াহিয়ার
    0.45
    的文章
    0.45
    homotopic
    0.45
    طور
    0.45
     dígitos
    0.43
    POSITIVE LOGITS
     *
    0.45
    "*
    0.45
    >
    0.44
    かし
    0.43
     този
    0.42
     befind
    0.42
    "
    0.42
     Besch
    0.41
    myTransform
    0.41
    '
    0.41
    Act Density 0.001%

    No Known Activations