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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ає
    -0.07
    _Return
    -0.07
    کور
    -0.07
     "@
    -0.06
     grosse
    -0.06
     По
    -0.06
     Sund
    -0.06
    -ac
    -0.06
    вся
    -0.06
     Warp
    -0.06
    POSITIVE LOGITS
     getLast
    0.07
     Dex
    0.06
     Scalars
    0.06
    ामल
    0.06
    Extreme
    0.06
    _shortcode
    0.06
    yles
    0.06
    برد
    0.06
    ardo
    0.06
     engagement
    0.06
    Act Density 0.001%

    No Known Activations