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

    Neuronpedia

    INDEX
    Explanations

    Research methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    픽
    -0.07
     Поп
    -0.07
     Sell
    -0.06
    Expose
    -0.06
     physics
    -0.06
    žel
    -0.06
    pons
    -0.06
     ARRAY
    -0.06
     много
    -0.06
    разд
    -0.06
    POSITIVE LOGITS
     المعلومات
    0.07
     مرکز
    0.07
    γωγή
    0.07
    $msg
    0.06
    ="/">↵
    0.06
    _URI
    0.06
    (alias
    0.06
     versatile
    0.06
    -o
    0.06
    -options
    0.06
    Act Density 0.021%

    No Known Activations