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

    Neuronpedia

    INDEX
    Explanations

    Formal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.50
     fiecare
    -0.48
     hipó
    -0.47
     perdon
    -0.47
     Fische
    -0.46
     Escolar
    -0.45
    ztály
    -0.45
     Gare
    -0.44
     innehå
    -0.44
     avoient
    -0.43
    POSITIVE LOGITS
    migrationBuilder
    0.65
    RectangleBorder
    0.62
    цездатний
    0.61
    EndContext
    0.60
    存于互联网档案馆
    0.59
    MLLoader
    0.59
    NegativeButton
    0.59
    llung
    0.58
    ukul
    0.58
     useParams
    0.58
    Act Density 0.107%

    No Known Activations