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

    Neuronpedia

    INDEX
    Explanations

    numbers inside brackets or standalone numbers

    oai_token-act-pair · gemini-2.0-flash

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ―――――
    -1.30
     Diſ
    -1.29
     Majefty
    -1.25
     Reſ
    -1.25
     Anſ
    -1.20
     Houſe
    -1.17
    ſelf
    -1.16
     itſelf
    -1.14
     ་་
    -1.14
    ſelves
    -1.14
    POSITIVE LOGITS
    <bos>
    1.20
     
    1.14
    '
    0.71
     N
    0.70
     S
    0.69
     "
    0.68
     I
    0.68
     A
    0.67
     G
    0.67
     “
    0.66
    Act Density 3.408%

    No Known Activations