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

    Neuronpedia

    INDEX
    Explanations

    articles "a" and "an"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.71
     or
    -0.59
     the
    -0.53
     other
    -0.53
     someone
    -0.52
     an
    -0.52
     any
    -0.51
     our
    -0.50
     either
    -0.50
     their
    -0.49
    POSITIVE LOGITS
     مشين
    0.89
     BoxDecoration
    0.88
     blessing
    0.77
     AssemblyTitle
    0.75
     ✭✭
    0.73
    WebControls
    0.72
    ^(@)
    0.66
     boon
    0.66
     useRouter
    0.65
     disgrace
    0.65
    Act Density 0.356%

    No Known Activations