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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cx
    -0.07
    __[
    -0.07
    خة
    -0.06
     Tulsa
    -0.06
    旗
    -0.06
     Prince
    -0.06
    (assign
    -0.06
    decoded
    -0.06
    nemonic
    -0.06
    919
    -0.06
    POSITIVE LOGITS
     experience
    0.09
     Experience
    0.08
     experiences
    0.07
     中
    0.07
    getting
    0.07
    ink
    0.06
     expérience
    0.06
     입
    0.06
    atar
    0.06
    lux
    0.06
    Act Density 0.015%

    No Known Activations