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

    Neuronpedia

    INDEX
    Explanations

    say "equals sign or capital letter"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workplace
    -0.07
     shoulder
    -0.07
     today
    -0.07
     resc
    -0.07
    	users
    -0.07
     paper
    -0.06
     qa
    -0.06
     hangs
    -0.06
     software
    -0.06
    %",
    -0.06
    POSITIVE LOGITS
    ologi
    0.06
     Shortcut
    0.06
    ioms
    0.06
     пример
    0.06
    uada
    0.06
     ekonom
    0.06
    ext
    0.06
    ฉ
    0.06
     sailors
    0.06
    captures
    0.06
    Act Density 0.007%

    No Known Activations