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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noqa
    -0.63
    devise
    -0.51
    FunctionFlags
    -0.49
    HasAnnotation
    -0.43
     living
    -0.43
     complex
    -0.41
    enumerable
    -0.41
    unjang
    -0.40
    OrNil
    -0.40
    $__
    -0.39
    POSITIVE LOGITS
    TagMode
    0.81
    ագրություններ
    0.74
    Hentet
    0.71
    målet
    0.69
    ADELPHIA
    0.63
    nių
    0.63
    AddHtmlAttribute
    0.62
     smtplib
    0.62
     estekak
    0.59
     مشين
    0.58
    Act Density 0.006%

    No Known Activations