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

    Neuronpedia

    INDEX
    Explanations

    books and pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pr
    -0.56
    b
    -0.56
    der
    -0.54
     b
    -0.51
     '
    -0.51
    migrationBuilder
    -0.51
     page
    -0.50
     si
    -0.50
     "
    -0.50
     ga
    -0.49
    POSITIVE LOGITS
     itſelf
    0.93
     becauſe
    0.82
     themſelves
    0.81
     leſs
    0.81
     myſelf
    0.81
     poffible
    0.80
     Jefus
    0.77
     faſt
    0.77
     Monfieur
    0.74
     ſeveral
    0.74
    Act Density 0.052%

    No Known Activations