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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preced
    -0.07
    :black
    -0.07
     hym
    -0.07
    유
    -0.07
    -li
    -0.07
     měl
    -0.07
    цо
    -0.06
     macOS
    -0.06
    ávka
    -0.06
     burns
    -0.06
    POSITIVE LOGITS
     eng
    0.07
    kont
    0.06
     Represent
    0.06
    ["
    0.06
     raised
    0.06
    compress
    0.06
     distorted
    0.06
    /articles
    0.06
    /connect
    0.06
    Observer
    0.06
    Act Density 0.046%

    No Known Activations