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

    Neuronpedia

    INDEX
    Explanations

    actions/behaviors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.12
     Theſe
    -1.12
     purpoſe
    -1.09
     Chriftian
    -1.05
     greateſt
    -1.02
     ſche
    -1.02
     Majefty
    -1.02
     Reſ
    -1.01
     Houſe
    -1.01
     Diſ
    -0.98
    POSITIVE LOGITS
     to
    0.69
     or
    0.54
    s
    0.47
     in
    0.46
    ets
    0.42
     of
    0.42
     and
    0.41
     (
    0.41
     that
    0.41
    .
    0.41
    Act Density 0.056%

    No Known Activations