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

    Neuronpedia

    INDEX
    Explanations

    good or nice quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.57
    an
    0.42
    at
    0.41
    es
    0.37
    w
    0.36
    0.35
    f
    0.35
    ed
    0.35
     s
    0.34
    uk
    0.34
    POSITIVE LOGITS
    ляє
    0.37
    καν
    0.35
    のか
    0.33
    ลงทุน
    0.33
    대
    0.33
    نا
    0.32
    לי
    0.32
    ادی
    0.32
    या
    0.31
    લી
    0.31
    Act Density 0.496%

    No Known Activations