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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    黨
    -0.07
    981
    -0.06
     Knife
    -0.06
     бюдж
    -0.06
    %"),↵
    -0.06
     captain
    -0.06
     Architecture
    -0.06
     thermal
    -0.06
     shirt
    -0.06
     depression
    -0.06
    POSITIVE LOGITS
    -ln
    0.07
     ukáz
    0.07
    idd
    0.07
     toes
    0.07
    aisal
    0.07
    (ro
    0.07
    mızı
    0.07
    (flag
    0.07
    alış
    0.06
    flex
    0.06
    Act Density 0.157%

    No Known Activations