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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     financières
    -0.68
     löyty
    -0.67
     prisonniers
    -0.65
    #+#
    -0.62
     näky
    -0.60
     appartenant
    -0.60
     Grecs
    -0.60
     hjer
    -0.59
     meille
    -0.58
     økonom
    -0.58
    POSITIVE LOGITS
    wards
    0.81
    lably
    0.60
     passing
    0.60
    WARDS
    0.60
    nesses
    0.59
    sides
    0.59
     to
    0.59
    passing
    0.58
    sted
    0.58
    lessly
    0.57
    Act Density 0.087%

    No Known Activations