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
     دیر
    0.81
    今回は
    0.76
    今回の
    0.75
    س
    0.74
    تاز
    0.73
     singlet
    0.71
     ayer
    0.70
    이번
    0.70
     దూ
    0.69
    ಣಿ
    0.68
    POSITIVE LOGITS
     silam
    1.63
     میل
    1.54
    -
    1.46
     onwards
    1.43
     году
    1.42
    년
    1.40
    -'
    1.39
    年
    1.37
    ″
    1.36
     সালের
    1.35
    Act Density 0.065%

    No Known Activations