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

    Neuronpedia

    INDEX
    Explanations

    penance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -1.61
     myſelf
    -1.51
     Monfieur
    -1.51
     purpoſe
    -1.43
     ſeveral
    -1.43
     Anſ
    -1.42
     Diſ
    -1.41
     pleaſure
    -1.38
     ſtate
    -1.34
     ſever
    -1.33
    POSITIVE LOGITS
    ed
    0.88
    ing
    0.73
     O
    0.71
    PRNewswire
    0.70
     H
    0.66
     "
    0.65
     I
    0.64
     P
    0.63
     C
    0.63
     '
    0.63
    Act Density 1.362%

    No Known Activations