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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -0.80
    .
    -0.71
     and
    -0.66
     In
    -0.64
    -
    -0.63
     For
    -0.63
    i
    -0.60
    (
    -0.59
     So
    -0.59
     With
    -0.59
    POSITIVE LOGITS
    脚注の使い方
    1.22
    IUrlHelper
    1.15
     autorytatywna
    1.13
    LookAnd
    1.05
    MLLoader
    1.05
    BibitemShut
    1.05
    tagHelperRunner
    1.02
    :✨
    1.01
     doubtnut
    1.01
    styleType
    0.98
    Act Density 0.032%

    No Known Activations