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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.83
     introduction
    0.71
     rep
    0.70
    introduction
    0.70
     perfectly
    0.70
    quote
    0.70
    view
    0.69
    ?
    0.67
    क्रम
    0.65
    vie
    0.63
    POSITIVE LOGITS
     "*************
    1.10
    தெ
    0.99
    耑
    0.99
     filenames
    0.99
    <unused1649>
    0.98
    ्योपै
    0.97
    ษัท
    0.97
    원본파일명
    0.97
    پيديا
    0.97
    初回
    0.97
    Act Density 0.005%

    No Known Activations