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

    Neuronpedia

    INDEX
    Explanations

    Names and birthplace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.48
     trous
    -0.44
    od
    -0.44
    rud
    -0.42
    kó
    -0.42
    жа
    -0.41
    æus
    -0.41
    odo
    -0.40
    cast
    -0.40
    ria
    -0.39
    POSITIVE LOGITS
    InjectAttribute
    1.13
    aarrggbb
    1.12
     '\\;'
    1.12
     виправивши
    1.07
    awtextra
    1.05
    uxxxx
    1.01
    1.01
    verwijspagina
    0.99
     typelib
    0.99
    ValueStyle
    0.98
    Act Density 0.231%
    No Known Activations