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

    Neuronpedia

    INDEX
    Explanations

    words related to education and sports

    oai_token-act-pair · gemini-2.0-flash

    High

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.32
     Theſe
    -1.27
     Efq
    -1.27
     myſelf
    -1.23
     ſhe
    -1.21
     himſelf
    -1.19
     Monfieur
    -1.18
     ſeveral
    -1.16
     whoſe
    -1.16
     ſever
    -1.15
    POSITIVE LOGITS
    ↵↵
    0.98
    ↵
    0.91
     
    0.68
     (
    0.63
    1
    0.63
    '
    0.63
     I
    0.60
    2
    0.59
     *
    0.58
    I
    0.58
    Act Density 0.961%

    No Known Activations