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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,name
    -0.07
     Commissioners
    -0.07
     очист
    -0.06
    ;?>
    -0.06
    เศ
    -0.06
     cloak
    -0.06
     analyze
    -0.06
    идент
    -0.06
    帯
    -0.06
    alardan
    -0.06
    POSITIVE LOGITS
     Pillow
    0.07
    enin
    0.07
    .ob
    0.07
     Sil
    0.07
    .slim
    0.06
     Anglic
    0.06
     pla
    0.06
    ()='
    0.06
    .play
    0.06
    .c
    0.06
    Act Density 0.019%

    No Known Activations