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

    Neuronpedia

    INDEX
    Explanations

    they/'t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .diff
    -0.07
    .gamma
    -0.06
     benim
    -0.06
    .angle
    -0.06
     Dropbox
    -0.06
     pir
    -0.06
     duly
    -0.06
    -do
    -0.06
     thinks
    -0.06
    輯
    -0.06
    POSITIVE LOGITS
     변화
    0.06
     Dickinson
    0.06
     φω
    0.06
    ClientId
    0.06
    ωτερ
    0.06
     Currently
    0.06
     noct
    0.06
    eless
    0.06
    Required
    0.06
    σταση
    0.05
    Act Density 0.061%

    No Known Activations