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

    Neuronpedia

    INDEX
    Explanations

    recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Member
    -0.07
    Arrow
    -0.07
    -rays
    -0.07
    _particle
    -0.06
    Hdr
    -0.06
     Pg
    -0.06
    ुल
    -0.06
    ün
    -0.06
     hàng
    -0.06
     fly
    -0.06
    POSITIVE LOGITS
     accord
    0.06
    ihu
    0.06
     uč
    0.06
    ・━・━・━・━
    0.06
     sexes
    0.06
     ornaments
    0.06
    ...↵
    0.06
     discrimination
    0.06
    握
    0.06
    _fc
    0.06
    Act Density 0.011%

    No Known Activations