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

    Neuronpedia

    INDEX
    Explanations

    changed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     changed
    -1.18
    changed
    -1.00
     replaced
    -0.97
     Changed
    -0.93
     tartalomajánló
    -0.90
     Replaced
    -0.82
    replaced
    -0.80
     EconPapers
    -0.80
    tagHelperRunner
    -0.76
     evolved
    -0.76
    POSITIVE LOGITS
     the
    0.70
     an
    0.66
     and
    0.65
    .
    0.63
     a
    0.60
     it
    0.60
     this
    0.60
     with
    0.59
     addition
    0.58
    digen
    0.57
    Act Density 0.016%

    No Known Activations