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

    Neuronpedia

    INDEX
    Explanations

    for loops ending in semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”…
    0.43
    那些
    0.38
     tripartite
    0.38
    န်
    0.37
    ذي
    0.37
     artístico
    0.37
    ’.
    0.36
     goodies
    0.36
     می‌تواند
    0.35
    धाम
    0.35
    POSITIVE LOGITS
     ;
    0.48
     she
    0.46
     Чер
    0.43
    cing
    0.43
    Cat
    0.42
    ination
    0.41
     ؛
    0.40
    )]
    0.40
     முடிவு
    0.40
     ;$
    0.40
    Act Density 0.067%

    No Known Activations