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

    Neuronpedia

    INDEX
    Explanations

    parts of Java source code related to managing fields in API requests

    oai_token-act-pair · gemini-2.0-flash

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.90
    ...
    -0.87
     -
    -0.85
    .
    -0.84
     '
    -0.84
    ↵
    -0.84
    …
    -0.81
     ‘
    -0.77
    ?
    -0.77
     R
    -0.77
    POSITIVE LOGITS
     itſelf
    1.95
     myſelf
    1.92
     iſt
    1.80
     Efq
    1.78
    ſelf
    1.77
     ſeveral
    1.75
     Jefus
    1.74
     Majefty
    1.65
    ſelves
    1.63
     purpoſe
    1.63
    Act Density 1.416%

    No Known Activations