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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RESPONSE
    -0.07
    uplicates
    -0.06
    	X
    -0.06
    ')==
    -0.06
    -0.06
     stringify
    -0.06
     PLAN
    -0.06
    _pdf
    -0.06
     상황
    -0.06
     ан
    -0.06
    POSITIVE LOGITS
    ,label
    0.07
     Honour
    0.07
     etwa
    0.06
    開発
    0.06
    reece
    0.06
    celand
    0.06
     AUT
    0.06
     archaeological
    0.06
     هتل
    0.06
     (~
    0.06
    Act Density 0.005%

    No Known Activations