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

    Neuronpedia

    INDEX
    Explanations

    Booker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Word
    -0.07
    ريس
    -0.06
     oferta
    -0.06
    _solve
    -0.06
    έλ
    -0.06
    ease
    -0.06
    (cube
    -0.06
     又
    -0.06
    業務
    -0.06
     sóng
    -0.06
    POSITIVE LOGITS
     [],↵
    0.07
     Marxism
    0.07
    う
    0.07
     intellectually
    0.06
    imming
    0.06
    scoped
    0.06
     Russell
    0.06
     spans
    0.06
     *[
    0.06
    Adjusted
    0.06
    Act Density 0.001%

    No Known Activations