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

    Neuronpedia

    INDEX
    Explanations

    umatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Atlanta
    -0.08
    pls
    -0.07
     안전
    -0.07
     paramMap
    -0.07
     culturally
    -0.07
    Nh
    -0.06
     Atlanta
    -0.06
    下来
    -0.06
     Cherokee
    -0.06
     sollen
    -0.06
    POSITIVE LOGITS
    umatic
    0.08
     Arthur
    0.07
    unic
    0.06
    icot
    0.06
    んで
    0.06
     Needed
    0.06
    _static
    0.06
    _FREQUENCY
    0.06
    discard
    0.06
     justice
    0.06
    Act Density 0.000%

    No Known Activations