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

    Neuronpedia

    INDEX
    Explanations

    HTML fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mination
    -0.07
    ceae
    -0.07
     Hind
    -0.07
    čan
    -0.06
    dings
    -0.06
     strom
    -0.06
    нение
    -0.06
    喜欢
    -0.06
     Lv
    -0.06
     ліка
    -0.06
    POSITIVE LOGITS
    dain
    0.07
     gw
    0.06
     deleg
    0.06
     );
    0.06
     Managers
    0.06
    ."),↵
    0.06
    ？↵
    0.06
     File
    0.06
    _Device
    0.06
     sortable
    0.06
    Act Density 0.031%

    No Known Activations