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

    Neuronpedia

    INDEX
    Explanations

    XML, burning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оке
    -0.07
     Torch
    -0.07
     unserem
    -0.07
    bek
    -0.06
    inand
    -0.06
    /player
    -0.06
     inmates
    -0.06
    _wo
    -0.06
     зміст
    -0.06
    pově
    -0.06
    POSITIVE LOGITS
    �
    0.08
     percentile
    0.07
     astronom
    0.07
     say
    0.07
     synonym
    0.06
    _fig
    0.06
     has
    0.06
    Segue
    0.06
     confirmation
    0.06
    -dd
    0.06
    Act Density 0.000%

    No Known Activations