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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fout
    -0.07
    .Export
    -0.07
    .Arg
    -0.07
    ten
    -0.06
     привести
    -0.06
     gå
    -0.06
    ору
    -0.06
    ывает
    -0.06
     Alive
    -0.06
    ocaust
    -0.06
    POSITIVE LOGITS
     deleting
    0.08
     народу
    0.07
    ilendir
    0.07
    __(
    0.07
     domácí
    0.07
     اجتماع
    0.07
    	TokenName
    0.07
     مسئله
    0.06
    เรา
    0.06
     ActiveSupport
    0.06
    Act Density 0.028%

    No Known Activations