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

    Neuronpedia

    INDEX
    Explanations

    wanted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вами
    -0.67
     oleh
    -0.66
    ︎
    -0.58
     prochaines
    -0.57
     disparu
    -0.56
     siècles
    -0.56
     posé
    -0.55
     <=",
    -0.55
     modalités
    -0.55
     by
    -0.54
    POSITIVE LOGITS
     a
    1.21
     the
    1.05
     to
    0.99
     an
    0.98
     some
    0.78
     another
    0.77
     any
    0.74
     them
    0.73
     it
    0.70
     his
    0.69
    Act Density 0.038%

    No Known Activations