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

    Neuronpedia

    INDEX
    Explanations

    function definitions and structure in programming code

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

    describe tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.63
    ſelves
    -0.60
     ſever
    -0.60
     ſte
    -0.59
     ſeveral
    -0.57
     itſelf
    -0.57
    CloseOperation
    -0.54
     ſind
    -0.54
     JTable
    -0.53
     ſtill
    -0.53
    POSITIVE LOGITS
    describe
    0.69
     describe
    0.63
     spec
    0.48
     Describe
    0.48
     description
    0.46
     describing
    0.45
     Cypress
    0.44
     descriptions
    0.43
     descriptive
    0.43
     describes
    0.42
    Act Density 0.011%

    No Known Activations