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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delt
    -0.06
     tree
    -0.06
     forma
    -0.06
     competitiveness
    -0.06
     Coat
    -0.06
    UTES
    -0.06
     、
    -0.06
     curtains
    -0.06
     фото
    -0.06
    (view
    -0.06
    POSITIVE LOGITS
    -viol
    0.07
    ۰۰۰
    0.07
    -private
    0.07
    sms
    0.07
    uese
    0.06
    	is
    0.06
     is
    0.06
    ivol
    0.06
    .errorMessage
    0.06
    \Unit
    0.06
    Act Density 0.048%

    No Known Activations