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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     axes
    -0.79
    uxxxx
    -0.73
     Axes
    -0.71
    #
    -0.65
    riwal
    -0.65
    ukone
    -0.65
     sandbox
    -0.62
    __":
    -0.59
    FormTagHelper
    -0.59
     traverse
    -0.58
    POSITIVE LOGITS
     وتسجيلات
    0.65
     kasarigan
    0.54
     lenker
    0.51
     المعيارى
    0.50
    able
    0.50
     Administrativna
    0.48
    ="@+
    0.48
    ður
    0.48
    hintText
    0.48
    väg
    0.47
    Act Density 0.845%

    No Known Activations