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

    Neuronpedia

    INDEX
    Explanations

    competitor analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mismos
    0.45
     동일
    0.42
     COMPANY
    0.40
     같은
    0.39
     шесть
    0.39
    lenme
    0.39
    caya
    0.39
    ში
    0.38
    같은
    0.38
     모집
    0.37
    POSITIVE LOGITS
    降
    0.41
    itivo
    0.41
    毌
    0.39
    ianus
    0.39
    结局
    0.37
    ிழ
    0.37
     Parks
    0.36
    uctive
    0.36
    intah
    0.36
    ucion
    0.36
    Act Density 0.012%

    No Known Activations