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

    Neuronpedia

    INDEX
    Explanations

    20

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -op
    -0.07
     прок
    -0.07
    odí
    -0.06
     trailers
    -0.06
     الخاص
    -0.06
    ')->
    -0.06
     ansch
    -0.06
     PM
    -0.06
    ».↵↵
    -0.06
    ↵	↵
    -0.06
    POSITIVE LOGITS
    Copying
    0.07
    ообраз
    0.07
     Creates
    0.06
     discoveries
    0.06
     Browns
    0.06
    Split
    0.06
    ві
    0.06
    fg
    0.06
    split
    0.06
    _cells
    0.06
    Act Density 0.007%

    No Known Activations