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

    Neuronpedia

    INDEX
    Explanations

    code, math equations, and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    code/programming strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.96
     myſelf
    -1.84
     Houſe
    -1.80
     ―――――
    -1.77
    ^(@)
    -1.74
     Majefty
    -1.73
     $_"
    -1.71
     Anſ
    -1.69
     raiſ
    -1.67
     Jefus
    -1.65
    POSITIVE LOGITS
    <bos>
    2.02
     
    1.10
    '
    1.06
    ↵↵
    1.00
    ↵
    1.00
     a
    0.96
     the
    0.91
    ’
    0.90
    O
    0.90
    .
    0.89
    Act Density 1.802%

    No Known Activations