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

    Neuronpedia

    INDEX
    Explanations

    sexual content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    98
    -0.07
     comport
    -0.07
     Avenue
    -0.07
     calories
    -0.06
     Marketing
    -0.06
     Laundry
    -0.06
     skull
    -0.06
     Supervisor
    -0.06
     PARA
    -0.06
     absorb
    -0.06
    POSITIVE LOGITS
    (ray
    0.09
    ():
    0.07
    	work
    0.07
     業
    0.06
    lluminate
    0.06
    055
    0.06
    pai
    0.06
     #'
    0.06
    宿
    0.06
     setStatus
    0.06
    Act Density 0.227%

    No Known Activations