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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transport
    -0.07
     inser
    -0.06
    チャ
    -0.06
    	min
    -0.06
     buttonText
    -0.06
     ling
    -0.06
     درد
    -0.06
     deal
    -0.06
    odos
    -0.06
     protests
    -0.06
    POSITIVE LOGITS
     впол
    0.07
    (locale
    0.07
    _refs
    0.07
     ebooks
    0.06
     Rockies
    0.06
    Formatter
    0.06
    ytt
    0.06
     Victims
    0.06
     Dispose
    0.06
    (atom
    0.06
    Act Density 0.204%

    No Known Activations