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

    Neuronpedia

    INDEX
    Explanations

    R&D

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.18
    ，
    1.03
    ،
    1.02
    。
    0.94
    、
    0.93
    ol
    0.78
    มัน
    0.74
     transducer
    0.73
    apal
    0.73
    గర
    0.72
    POSITIVE LOGITS
    ка
    1.67
    на
    1.60
    ك
    1.47
    و
    1.33
    ラ
    1.33
    아
    1.24
    я
    1.23
    اد
    1.17
    া
    1.13
    ير
    1.12
    Act Density 0.015%

    No Known Activations