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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÉRI
    0.44
    Blanc
    0.43
    шер
    0.43
    État
    0.42
    波数
    0.42
    Noir
    0.41
     достат
    0.41
    ПА
    0.41
    ПУ
    0.40
    ViewState
    0.40
    POSITIVE LOGITS
     example
    0.73
     ejemplo
    0.69
     exemple
    0.66
     exemplo
    0.66
     exemplu
    0.63
     esempio
    0.63
     contoh
    0.62
    example
    0.62
     Example
    0.60
    也可以
    0.59
    Act Density 0.476%

    No Known Activations