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

    Neuronpedia

    INDEX
    Explanations

    is/'s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welding
    -0.07
     accesses
    -0.07
    浜
    -0.07
     hamburg
    -0.07
     Latina
    -0.06
    통령
    -0.06
     плав
    -0.06
    語
    -0.06
    лок
    -0.06
     simulate
    -0.06
    POSITIVE LOGITS
    "},
↵
    0.07
     모집
    0.06
    ERT
    0.06
     thiệu
    0.06
     Roberts
    0.06
     />
    0.06
    Discuss
    0.06
    %%%%%%%%
    0.06
    (get
    0.06
     achieving
    0.06
    Act Density 0.015%

    No Known Activations