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

    Neuronpedia

    INDEX
    Explanations

    function definitions and return statements in programming code

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

    Code paired parentheses/brackets

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation or brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -1.06
    SourceChecksum
    -0.96
     дописавши
    -0.86
     tartalomajánló
    -0.85
    ंदीखरीदारी
    -0.74
    kháu
    -0.71
     noDo
    -0.71
     kasarigan
    -0.70
     disponibilités
    -0.67
    });*/
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.70
     But
    0.70
     Then
    0.61
    But
    0.57
     However
    0.57
     Nevertheless
    0.56
     but
    0.53
    ↵↵↵
    0.52
     Indeed
    0.52
    else
    0.51
    Act Density 0.089%

    No Known Activations