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

    Neuronpedia

    INDEX
    Explanations

    presentation introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     верх
    0.39
     nú
    0.38
    archive
    0.38
    瞭
    0.37
    repl
    0.37
    ть
    0.36
    的研究
    0.36
    នុ
    0.36
     тара
    0.35
     цей
    0.35
    POSITIVE LOGITS
     Öncelikle
    0.46
     제가
    0.44
     फरक
    0.42
     servicemen
    0.42
     bandits
    0.41
    uyorum
    0.41
    aboutme
    0.41
     Où
    0.41
     unassuming
    0.40
    ժ
    0.40
    Act Density 0.002%

    No Known Activations