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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hull
    -0.07
     skins
    -0.07
    .hm
    -0.07
     convex
    -0.07
    arrera
    -0.07
     collectors
    -0.07
    fen
    -0.07
    roud
    -0.07
     lect
    -0.07
    {:
    -0.07
    POSITIVE LOGITS
    imli
    0.06
    tgl
    0.06
    abcdefgh
    0.06
     Dairy
    0.06
    kaç
    0.06
    HTTPS
    0.06
     Kanye
    0.06
     ім
    0.06
     yarat
    0.06
     Γι
    0.06
    Act Density 0.037%

    No Known Activations