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

    Neuronpedia

    INDEX
    Explanations

    loops and generators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    选中
    0.42
    法轮
    0.41
    耱
    0.41
    pieceSelection
    0.40
     परमा
    0.40
    畚
    0.39
     actinides
    0.38
    یثیت
    0.38
     lunches
    0.37
     cela
    0.37
    POSITIVE LOGITS
    loop
    0.51
     loop
    0.47
     looping
    0.47
     LOOP
    0.46
    ループ
    0.42
    laid
    0.42
    fol
    0.41
     Loop
    0.41
     loops
    0.40
    Loops
    0.40
    Act Density 0.001%

    No Known Activations