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

    Neuronpedia

    INDEX
    Explanations

    closing braces in code structures

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

    Code blocks, especially closing code

    np_acts-logits-general · gemini-2.0-flash

    conditional else block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.03
    évaluateur
    -1.01
    MigrationBuilder
    -1.01
     itſelf
    -0.93
    +#+
    -0.91
     myſelf
    -0.88
     rhestr
    -0.88
     Theſe
    -0.87
     Monfieur
    -0.87
     Efq
    -0.86
    POSITIVE LOGITS
     else
    1.58
    else
    1.25
     other
    0.97
     others
    0.85
    否则
    0.69
     ELSE
    0.68
     altro
    0.68
     demás
    0.66
     elsewhere
    0.65
     otherwise
    0.65
    Act Density 0.056%

    No Known Activations