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

    Neuronpedia

    INDEX
    Explanations

    working together

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thắng
    -0.07
    ervlet
    -0.06
    hpp
    -0.06
    ΡΙ
    -0.06
     erratic
    -0.06
    �
    -0.06
    anooga
    -0.06
    -т
    -0.06
    ampp
    -0.06
    -ing
    -0.06
    POSITIVE LOGITS
     работает
    0.06
    -Semitism
    0.06
    (levels
    0.06
     Герм
    0.06
    (begin
    0.06
     arou
    0.06
     juices
    0.06
    [arg
    0.06
     Donna
    0.06
     diseñ
    0.06
    Act Density 0.132%

    No Known Activations