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

    Neuronpedia

    INDEX
    Explanations

    not precisely, but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    同时
    0.83
    /
    0.81
     ஆகியவை
    0.81
    同步
    0.79
    Select
    0.77
    同樣
    0.76
    Additionally
    0.76
    ्या
    0.76
    Via
    0.75
    }/
    0.75
    POSITIVE LOGITS
     nor
    1.75
     only
    1.67
     merely
    1.67
    only
    1.57
     лишь
    1.47
     hanya
    1.44
     केवल
    1.41
     apenas
    1.41
     Only
    1.40
    nor
    1.38
    Act Density 0.076%

    No Known Activations