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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    运
    -0.07
    Lex
    -0.07
     Hugo
    -0.06
    čný
    -0.06
     Fury
    -0.06
    (factory
    -0.06
     Nass
    -0.06
    нок
    -0.06
    .Groups
    -0.06
    pageNum
    -0.06
    POSITIVE LOGITS
     ارائه
    0.07
    —to
    0.07
    (CL
    0.07
     �
    0.07
    NODE
    0.07
     capturing
    0.06
     received
    0.06
    сім
    0.06
    apsed
    0.06
    ο
    0.06
    Act Density 0.389%

    No Known Activations