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

    Neuronpedia

    INDEX
    Explanations

    the word "entry" and short words nearby

    oai_token-act-pair · gemini-2.0-flash

    entry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.71
     Monfieur
    -1.50
     pleaſure
    -1.49
     Majefty
    -1.48
     Reſ
    -1.48
     Houſe
    -1.46
     Anſ
    -1.45
     Jefus
    -1.45
     Shakspeare
    -1.45
     itſelf
    -1.45
    POSITIVE LOGITS
     I
    0.66
     
    0.65
     $
    0.63
     a
    0.63
    i
    0.56
     about
    0.56
     just
    0.56
    zugehen
    0.55
     (
    0.55
     in
    0.54
    Act Density 2.453%

    No Known Activations