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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     /\.(
    -0.51
     intptr
    -0.51
    RegressionTest
    -0.51
    ydney
    -0.49
    êmio
    -0.47
    reid
    -0.47
    urgi
    -0.47
     Biôgrafia
    -0.46
    cloudfront
    -0.44
     Usually
    -0.44
    POSITIVE LOGITS
    ResumeLayout
    0.57
    TryParse
    0.56
     chick
    0.56
     skuto
    0.53
     IndexError
    0.52
    ']->
    0.52
     Chick
    0.51
     дописавши
    0.51
    laka
    0.50
     SONS
    0.50
    Act Density 0.010%

    No Known Activations