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

    Neuronpedia

    INDEX
    Explanations

    distinguishing robots from humans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mbH
    -0.07
    /schema
    -0.07
    conda
    -0.06
     ortam
    -0.06
     Kiş
    -0.06
     कर
    -0.06
    ตะ
    -0.06
    BUILD
    -0.06
    currentUser
    -0.06
    /raw
    -0.06
    POSITIVE LOGITS
    ----
    0.07
    ,class
    0.06
    ριος
    0.06
    >`;↵
    0.06
     carte
    0.06
     let
    0.06
    (updated
    0.06
     arranging
    0.06
     ск
    0.06
     fakat
    0.06
    Act Density 0.002%

    No Known Activations