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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keycode
    -0.09
    鸲
    -0.07
    CT
    -0.07
     favorable
    -0.07
     XK
    -0.07
    Submit
    -0.07
     giữa
    -0.07
     JW
    -0.07
     già
    -0.07
     energ
    -0.07
    POSITIVE LOGITS
     ülkeler
    0.07
    salary
    0.06
     handing
    0.06
     ADDRESS
    0.06
    诲
    0.06
    /java
    0.06
     media
    0.06
    ご
    0.06
    ଽ
    0.06
     Thickness
    0.06
    Act Density 0.008%

    No Known Activations