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

    Neuronpedia

    INDEX
    Explanations

    bash scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Xamarin
    0.82
     ២
    0.77
    ܘܢ
    0.75
    ائيل
    0.73
    ேஷ்
    0.73
    yyam
    0.72
    attho
    0.71
    éfonos
    0.71
    ᖓ
    0.71
    సూరు
    0.70
    POSITIVE LOGITS
    Ans
    0.75
    !\
    0.73
     মেশ
    0.70
    Bin
    0.67
    確か
    0.66
    Po
    0.66
    に向
    0.66
    の
    0.64
    р
    0.64
    нг
    0.63
    Act Density 0.035%

    No Known Activations