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

    Neuronpedia

    INDEX
    Explanations

    technical writing excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'all
    -0.07
    pai
    -0.07
     자연
    -0.07
    漂
    -0.07
    قية
    -0.07
     forfeiture
    -0.06
     polarity
    -0.06
    $filter
    -0.06
    	LCD
    -0.06
    _QUAL
    -0.06
    POSITIVE LOGITS
     Kişisel
    0.07
     counseling
    0.06
     Counseling
    0.06
     phases
    0.06
     valued
    0.06
     місці
    0.06
    大的
    0.06
     =>'
    0.06
     elected
    0.06
     bool
    0.06
    Act Density 0.000%

    No Known Activations