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

    Neuronpedia

    INDEX
    Explanations

    programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ملت
    -0.07
    _head
    -0.06
    ©©
    -0.06
    .Grid
    -0.06
    .spy
    -0.06
    济
    -0.06
     Garr
    -0.06
    _FACTORY
    -0.06
     Jest
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    	queue
    0.07
    	check
    0.07
    	page
    0.06
    -employed
    0.06
    مق
    0.06
     Established
    0.06
    moves
    0.06
    ालय
    0.06
     outfit
    0.06
    atas
    0.06
    Act Density 0.000%

    No Known Activations