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

    Neuronpedia

    INDEX
    Explanations

    cells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ".$_
    -0.08
    _solution
    -0.07
     ajax
    -0.07
    semb
    -0.07
     internal
    -0.07
    wcs
    -0.06
    ivos
    -0.06
    Cab
    -0.06
     workload
    -0.06
     delays
    -0.06
    POSITIVE LOGITS
     kvinn
    0.06
     smě
    0.06
     stup
    0.06
    (Collectors
    0.06
     夏
    0.06
     kişilerin
    0.06
    	getline
    0.06
     �
    0.06
     있는데
    0.06
     인천
    0.06
    Act Density 0.013%

    No Known Activations