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

    Neuronpedia

    INDEX
    Explanations

    as a measure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    স
    2.05
    𝐬
    1.97
    ות
    1.90
    𝐫
    1.72
    𝐭
    1.70
    સ
    1.61
    atás
    1.59
     বালক
    1.59
    डे
    1.55
    ot
    1.55
    POSITIVE LOGITS
     Fortunately
    2.07
     esto
    1.82
    carriage
    1.74
     alttext
    1.73
     "");
    1.72
     scrollTo
    1.67
    <unused1124>
    1.66
     Luckily
    1.65
     kompos
    1.62
     এসময়
    1.62
    Act Density 0.000%

    No Known Activations