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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     默认
    -0.07
    /a
    -0.07
     الع
    -0.07
     ware
    -0.06
     sits
    -0.06
    theme
    -0.06
    obs
    -0.06
    ursions
    -0.06
     moms
    -0.06
    _my
    -0.06
    POSITIVE LOGITS
     nữ
    0.08
    odore
    0.07
    lop
    0.07
    owntown
    0.06
    _ABI
    0.06
    ikit
    0.06
    وط
    0.06
    .uf
    0.06
    .ttf
    0.06
    Dem
    0.06
    Act Density 0.001%

    No Known Activations