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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     readings
    -0.07
    -is
    -0.07
    663
    -0.07
    Construct
    -0.06
    cdr
    -0.06
    DI
    -0.06
     Düz
    -0.06
    _mb
    -0.06
    enser
    -0.06
    slider
    -0.06
    POSITIVE LOGITS
     NVIC
    0.07
    mez
    0.07
    нова
    0.06
     평균
    0.06
     волос
    0.06
    Late
    0.06
    부터
    0.06
    )';↵
    0.06
     눈을
    0.06
    atonin
    0.06
    Act Density 0.067%

    No Known Activations