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

    Neuronpedia

    INDEX
    Explanations

    even fall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     należy
    0.39
    ರುವುದರಿಂದ
    0.39
    但是在
    0.37
    你需要
    0.37
    ঃখ
    0.37
    เกี่ยวกับ
    0.37
     zuverläss
    0.37
     rich
    0.35
     Hlav
    0.35
     তীরে
    0.35
    POSITIVE LOGITS
     sogar
    2.02
    甚至
    1.93
     zelfs
    1.93
     addirittura
    1.90
     даже
    1.80
     bahkan
    1.78
     even
    1.77
     thậm
    1.73
     навіть
    1.68
    甚至是
    1.67
    Act Density 0.476%

    No Known Activations