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

    Neuronpedia

    INDEX
    Explanations

    code and logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LED
    -0.07
    customers
    -0.07
     Çok
    -0.07
     calculation
    -0.07
     RNG
    -0.07
    dup
    -0.07
    .Simple
    -0.07
     DIN
    -0.06
     GANG
    -0.06
     IDM
    -0.06
    POSITIVE LOGITS
    eb
    0.06
    ことが
    0.06
     capit
    0.06
     úspě
    0.06
    todo
    0.06
    -war
    0.06
    olut
    0.06
    -equ
    0.06
     phụ
    0.06
     lời
    0.06
    Act Density 0.075%

    No Known Activations