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

    Neuronpedia

    INDEX
    Explanations

    latest versions and later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    month
    0.41
    ধা
    0.40
    月に
    0.39
    bulan
    0.38
    ศาส
    0.37
    ']*
    0.37
     month
    0.37
    сток
    0.36
     муниципалите
    0.36
    $.\\
    0.36
    POSITIVE LOGITS
     newer
    1.41
     Newer
    1.21
     latest
    1.13
    最新
    1.11
    最新的
    1.08
     newest
    1.07
    newer
    1.06
     Latest
    1.05
     terbaru
    1.03
    Latest
    1.02
    Act Density 0.044%

    No Known Activations