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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sock
    -0.07
     nhờ
    -0.07
     resumes
    -0.07
    }}}
    -0.07
    '})
    -0.07
     BuzzFeed
    -0.07
     шляхом
    -0.06
     アル
    -0.06
    )]
    -0.06
     MatTable
    -0.06
    POSITIVE LOGITS
     Dudley
    0.07
     lag
    0.07
    џџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџ
    0.07
     jq
    0.07
    ريقة
    0.06
     eliminar
    0.06
     eliminating
    0.06
     pz
    0.06
     Tec
    0.06
     Barbara
    0.06
    Act Density 0.010%

    No Known Activations