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

    Neuronpedia

    INDEX
    Explanations

    simple clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    keepers
    0.38
    ❸
    0.38
    宸
    0.37
     ઉપરા
    0.36
    recursion
    0.36
    LEC
    0.36
    southern
    0.36
    μέ
    0.36
    sendLog
    0.35
    emoration
    0.35
    POSITIVE LOGITS
     simple
    0.57
    简单
    0.55
     simples
    0.54
    簡單
    0.51
     간단
    0.50
     clearer
    0.47
     sederhana
    0.47
     semplice
    0.46
     cleaner
    0.46
     sane
    0.46
    Act Density 0.000%

    No Known Activations