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

    Neuronpedia

    INDEX
    Explanations

    svg and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hundred
    0.88
    Bulletin
    0.82
     inoxyd
    0.82
    maxX
    0.81
    ourent
    0.81
     atvej
    0.80
     únic
    0.80
    CHREIBUNG
    0.80
    uminação
    0.80
     الاقوامی
    0.77
    POSITIVE LOGITS
     impression
    0.70
     beyond
    0.62
     diverse
    0.61
     even
    0.59
     lifestyle
    0.59
     exceeding
    0.58
     imagined
    0.58
     spring
    0.58
     any
    0.58
     pit
    0.57
    Act Density 0.148%

    No Known Activations