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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     arithmetic
    -0.06
     enriched
    -0.06
     Puzzle
    -0.06
     chlorine
    -0.06
    %'
    -0.06
    <len
    -0.06
     assigned
    -0.06
     tab
    -0.06
     spo
    -0.06
    POSITIVE LOGITS
    يش
    0.07
    ibr
    0.07
     Autos
    0.07
    -equ
    0.06
    -of
    0.06
    ưởng
    0.06
    ارش
    0.06
    افت
    0.06
    enis
    0.06
    บค
    0.06
    Act Density 0.034%

    No Known Activations