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

    Neuronpedia

    INDEX
    Explanations

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಸೂ
    0.73
     stre
    0.69
     ♪
    0.67
    ភ្ល
    0.65
    olit
    0.65
     sebesar
    0.64
     좀
    0.63
     ঘুম
    0.63
     곳
    0.63
     abgest
    0.62
    POSITIVE LOGITS
    Year
    0.78
    century
    0.74
     century
    0.71
     Year
    0.70
    YEAR
    0.70
    upuncture
    0.69
    natural
    0.68
    ursed
    0.67
     YEAR
    0.67
    씀
    0.66
    Act Density 0.083%

    No Known Activations