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

    Neuronpedia

    INDEX
    Explanations

    code imports and includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     молеку
    0.40
     வாய்
    0.38
    ക്കൊ
    0.37
    ANGMAR
    0.36
     cannula
    0.36
     вікі
    0.36
     covariate
    0.36
    噉
    0.36
    痫
    0.36
    eteries
    0.35
    POSITIVE LOGITS
    import
    0.82
    #!/
    0.68
    <?
    0.57
    require
    0.55
    package
    0.55
    #![
    0.52
    <!
    0.51
    <%@
    0.50
    include
    0.49
    #
    0.48
    Act Density 0.059%

    No Known Activations