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

    Neuronpedia

    INDEX
    Explanations

    LaTeX packages and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udarstven
    0.35
     سلاٹ
    0.35
     کھولنے
    0.34
    enuh
    0.34
    桫
    0.34
     weiterer
    0.34
    雄
    0.34
    bulldozer
    0.33
     solidly
    0.33
     decadent
    0.33
    POSITIVE LOGITS
     defines
    0.37
    ↵
    0.36
     through
    0.35
    ↵↵
    0.35
    Sp
    0.34
     ;
    0.34
     define
    0.34
    定义
    0.34
    ;
    0.33
    ,
    0.33
    Act Density 0.001%

    No Known Activations