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

    Neuronpedia

    INDEX
    Explanations

    AI-powered driver, historical figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invas
    0.48
     вклад
    0.45
     pathologists
    0.44
     phenylalanine
    0.44
     Awakening
    0.43
    unbind
    0.43
     விள
    0.42
    %!
    0.42
    <unused173>
    0.42
    atik
    0.42
    POSITIVE LOGITS
    ли
    0.53
    зи
    0.52
    λλ
    0.49
    ו
    0.44
    ol
    0.43
    ાઇ
    0.43
     tạm
    0.42
    Mount
    0.41
    ificat
    0.41
    ot
    0.41
    Act Density 0.000%

    No Known Activations