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

    Neuronpedia

    INDEX
    Explanations

    research and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مان
    0.51
    리티
    0.48
    ных
    0.47
    <0xAB>
    0.47
    心
    0.46
    故事
    0.46
    不
    0.46
    手
    0.45
    न्या
    0.45
    0.45
    POSITIVE LOGITS
    in
    0.77
     in
    0.63
    IN
    0.63
    )];
    0.63
    ;
    0.61
     inorder
    0.60
     researches
    0.59
    ים
    0.59
    a
    0.59
    ;")
    0.58
    Act Density 0.379%

    No Known Activations