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

    Neuronpedia

    INDEX
    Explanations

    fabrication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fate
    -0.80
     Stardust
    -0.71
     atve
    -0.71
     stitch
    -0.70
     poffible
    -0.70
     Tivoli
    -0.69
     stitches
    -0.69
     faking
    -0.68
     Efq
    -0.68
     seat
    -0.66
    POSITIVE LOGITS
     of
    0.56
    plant
    0.51
    group
    0.49
     unknownFields
    0.48
    IntoConstraints
    0.46
    ings
    0.45
    ########.
    0.45
     autorytatywna
    0.44
    RegressionTest
    0.44
    room
    0.44
    Act Density 0.325%

    No Known Activations