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

    Neuronpedia

    INDEX
    Explanations

    numbers, code, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قاعدة
    0.69
    Box
    0.65
    Unit
    0.65
     Unit
    0.64
     Box
    0.64
     unid
    0.64
     unidade
    0.64
     Axis
    0.62
     Corn
    0.62
    ユニット
    0.61
    POSITIVE LOGITS
    एमपी
    0.64
     MP
    0.59
     পর্যায়ের
    0.59
    혐
    0.59
     verv
    0.58
    𝙨
    0.57
    ហ៊
    0.55
    mp
    0.55
     sos
    0.55
    slo
    0.55
    Act Density 0.099%

    No Known Activations