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

    Neuronpedia

    INDEX
    Explanations

    Questions/descriptions of magnitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    er
    -0.61
    veni
    -0.49
    net
    -0.48
    ers
    -0.48
    ity
    -0.47
    ty
    -0.45
    ural
    -0.45
     Mer
    -0.44
    kin
    -0.43
    king
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    1.05
    Diweddarwch
    0.94
     AssemblyTitle
    0.91
     виправивши
    0.87
     CreateTagHelper
    0.81
    expandindo
    0.81
     فريبيس
    0.77
     nahilalakip
    0.76
    GraphicsUnit
    0.75
     समीक्षक
    0.75
    Act Density 0.133%

    No Known Activations