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

    Neuronpedia

    INDEX
    Explanations

    regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -class
    -0.08
    _common
    -0.07
     IPS
    -0.07
    ximity
    -0.07
    AF
    -0.07
     نقد
    -0.07
    536
    -0.06
     females
    -0.06
    Factor
    -0.06
     Nuclear
    -0.06
    POSITIVE LOGITS
     \"$
    0.07
    ->{$
    0.06
     discusses
    0.06
    解决
    0.06
     seb
    0.06
     Newly
    0.06
    	Error
    0.06
     rst
    0.06
     yi
    0.06
     $#
    0.06
    Act Density 0.116%

    No Known Activations