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

    Neuronpedia

    INDEX
    Explanations

    comment syntax in code

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

    Code snippets with annotations

    np_acts-logits-general · gemini-2.0-flash

    code constructs and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lo
    -0.53
     tr
    -0.52
    fal
    -0.49
     sí
    -0.47
    itu
    -0.46
    ...
    -0.45
    -
    -0.44
    าน
    -0.44
     sv
    -0.44
     гу
    -0.44
    POSITIVE LOGITS
    tvguidetime
    1.02
    InjectAttribute
    1.00
    ftagPool
    0.94
    __':
    0.93
     ModelExpression
    0.93
    __":
    0.92
    principalTable
    0.88
    </tfoot>
    0.87
    BeginContext
    0.86
    )*/
    0.86
    Act Density 0.012%

    No Known Activations