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
    	cal
    -0.06
    셨
    -0.06
    .dirty
    -0.06
    _both
    -0.06
    òn
    -0.06
    .sd
    -0.06
    (stock
    -0.06
    	col
    -0.06
     speci
    -0.06
     sher
    -0.06
    POSITIVE LOGITS
     fichier
    0.08
    zyć
    0.07
    helpers
    0.07
    imensional
    0.07
     condemned
    0.07
    GO
    0.07
    ビー
    0.06
    ός
    0.06
    elleicht
    0.06
     migrations
    0.06
    Act Density 0.019%

    No Known Activations