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

    Neuronpedia

    INDEX
    Explanations

    prolonged duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    run
    -0.69
     run
    -0.65
    c
    -0.55
    h
    -0.53
    long
    -0.52
     (
    -0.51
    up
    -0.51
    b
    -0.51
    nd
    -0.50
     D
    -0.50
    POSITIVE LOGITS
     esternos
    0.98
     CreateTagHelper
    0.88
     myſelf
    0.87
     Efq
    0.84
    ArgsConstructor
    0.83
     Monfieur
    0.80
     itſelf
    0.77
     auffi
    0.77
     Anſ
    0.76
     reaſon
    0.75
    Act Density 0.138%

    No Known Activations