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

    Neuronpedia

    INDEX
    Explanations

    leading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leading
    -0.61
     man
    -0.59
     lead
    -0.55
    leading
    -0.54
     Man
    -0.47
     (
    -0.46
    Linki
    -0.45
     the
    -0.44
     men
    -0.43
    lead
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.96
     ſeveral
    0.91
    MigrationBuilder
    0.86
     Houſe
    0.84
     houſe
    0.79
    swire
    0.79
     faſt
    0.79
    |}{$
    0.79
     leaſt
    0.78
     itſelf
    0.78
    Act Density 0.034%

    No Known Activations