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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insertion
    -0.06
    461
    -0.06
     Lair
    -0.06
    lu
    -0.06
    ={"
    -0.06
     rol
    -0.05
    Mel
    -0.05
     wal
    -0.05
     cnn
    -0.05
     Nile
    -0.05
    POSITIVE LOGITS
     Packing
    0.07
    imap
    0.07
    _public
    0.06
     surprisingly
    0.06
    pic
    0.06
    iag
    0.06
    //@
    0.06
    (Float
    0.06
     apparently
    0.06
    $scope
    0.06
    Act Density 0.013%

    No Known Activations