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

    Neuronpedia

    INDEX
    Explanations

    the followed by common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kommen
    0.48
    metry
    0.46
    plete
    0.46
    build
    0.44
    ież
    0.44
    pf
    0.44
    optimal
    0.43
    <0x0B>
    0.43
    expand
    0.43
    ◊
    0.43
    POSITIVE LOGITS
    inama
    0.51
    થી
    0.49
    问题
    0.49
     کہا
    0.49
     implic
    0.48
    没有
    0.48
    情况下
    0.48
     arguably
    0.48
     मोटा
    0.47
    ڈ
    0.47
    Act Density 1.999%

    No Known Activations