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

    Neuronpedia

    INDEX
    Explanations

    resources and parameters related to computer programming and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Variables, abbreviations, or short names

    np_acts-logits-general · gemini-2.0-flash

    Numbers followed by 0 or 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.74
    .
    -0.72
    ↵
    -0.72
    ,
    -0.69
    <eos>
    -0.69
    ;
    -0.64
    ),
    -0.64
    )
    -0.61
    ↵↵↵
    -0.60
    :
    -0.60
    POSITIVE LOGITS
     Мексичка
    1.32
     يتيمه
    1.25
     myſelf
    1.22
     itſelf
    1.16
    PerformLayout
    1.13
     Efq
    1.11
     Jefus
    1.10
    PreferredItem
    1.09
    ItemBackground
    1.06
     Shakspeare
    1.04
    Act Density 0.859%

    No Known Activations