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

    Neuronpedia

    INDEX
    Explanations

    Final Answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    設け
    0.71
    లంగా
    0.68
     accumulated
    0.66
    elius
    0.66
     Bial
    0.65
    лением
    0.64
     Beagle
    0.64
     облег
    0.64
    ोजित
    0.64
     eml
    0.61
    POSITIVE LOGITS
     시
    0.80
    시
    0.76
    ردن
    0.67
     বিদ্যা
    0.64
     گ
    0.64
     書
    0.64
    রিদ
    0.63
    ரியில்
    0.63
    рона
    0.62
     Vis
    0.62
    Act Density 0.063%

    No Known Activations