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

    Neuronpedia

    INDEX
    Explanations

    source of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पं
    0.41
    deos
    0.38
    timed
    0.38
    Chance
    0.37
     яке
    0.37
     अधिक
    0.37
    льно
    0.36
    льное
    0.36
     관련
    0.36
    tolerance
    0.36
    POSITIVE LOGITS
     źród
    0.58
     fonti
    0.57
     sumber
    0.56
    来源
    0.55
     inspiration
    0.54
     zdroj
    0.53
     whence
    0.52
     sources
    0.52
     fontes
    0.51
     nguồn
    0.50
    Act Density 0.006%

    No Known Activations