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

    Neuronpedia

    INDEX
    Explanations

    After

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jong
    -0.07
     Ama
    -0.06
     Nah
    -0.06
     redesigned
    -0.06
     Hav
    -0.06
     比
    -0.06
    altitude
    -0.06
     Republic
    -0.06
    ервые
    -0.06
     actively
    -0.06
    POSITIVE LOGITS
    gzip
    0.07
     \/
    0.07
    Ensure
    0.07
     complied
    0.07
     inward
    0.07
     cómo
    0.06
    veal
    0.06
     PICK
    0.06
     knock
    0.06
     sợ
    0.06
    Act Density 0.027%

    No Known Activations