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

    Neuronpedia

    INDEX
    Explanations

    application or tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iš
    2.19
    ações
    1.87
    yun
    1.77
    yz
    1.71
    ação
    1.69
    aient
    1.66
    یل
    1.64
    yk
    1.64
    ে
    1.62
    ्यांना
    1.62
    POSITIVE LOGITS
     ause
    1.68
    に
    1.57
     infr
    1.54
    whitespace
    1.51
     enticing
    1.47
     overshadow
    1.46
     aching
    1.44
    un
    1.42
    쇄
    1.40
     demanding
    1.38
    Act Density 0.030%

    No Known Activations