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

    Neuronpedia

    INDEX
    Explanations

    Code and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FIXME
    -0.07
     idx
    -0.06
    	items
    -0.06
     projections
    -0.06
     ################################################
    -0.06
    =ax
    -0.06
     �
    -0.06
    充
    -0.06
     knees
    -0.06
     Baz
    -0.06
    POSITIVE LOGITS
    (hand
    0.07
    ?>↵↵
    0.07
    _LSB
    0.06
     Lat
    0.06
     Fleet
    0.06
     bevor
    0.06
    ськ
    0.06
    отя
    0.06
    +Sans
    0.06
     الخاص
    0.06
    Act Density 0.005%

    No Known Activations