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

    Neuronpedia

    INDEX
    Explanations

    use and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.42
    s
    0.41
    TE
    0.39
    á
    0.38
     e
    0.38
    م
    0.38
     o
    0.37
    nl
    0.37
    ä
    0.37
    ON
    0.36
    POSITIVE LOGITS
     penggunaan
    0.33
    जामा
    0.33
     cellulosic
    0.33
    快適
    0.33
    клада
    0.32
     agron
    0.32
     казіно
    0.32
     ayatan
    0.32
    양
    0.32
    羲
    0.31
    Act Density 0.066%

    No Known Activations