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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     striker
    -0.07
    ningar
    -0.07
    เคล
    -0.07
    managedType
    -0.06
     등록대행
    -0.06
    桐
    -0.06
    nya
    -0.06
    /$',
    -0.06
     ladder
    -0.06
    xcc
    -0.06
    POSITIVE LOGITS
     Fish
    0.06
     PACK
    0.06
     confused
    0.06
     VALUE
    0.06
     PROGRAM
    0.06
     Uygu
    0.06
    Floor
    0.06
    -book
    0.06
     tg
    0.05
    emek
    0.05
    Act Density 0.003%

    No Known Activations