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

    Neuronpedia

    INDEX
    Explanations

    code elements related to functions and methods in programming

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

    Code related to adding or trimming

    np_acts-logits-general · gemini-2.0-flash

    add or adding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Entered
    -0.46
    Joining
    -0.42
    unes
    -0.41
    inserted
    -0.39
     grafted
    -0.39
    entered
    -0.38
    included
    -0.38
    skrä
    -0.38
    inser
    -0.37
    olverine
    -0.37
    POSITIVE LOGITS
    add
    2.43
     add
    2.43
     Add
    2.10
    Add
    1.94
     adds
    1.51
     ADD
    1.43
    ADD
    1.39
     adding
    1.37
     Adds
    1.32
    添加
    1.20
    Act Density 0.072%

    No Known Activations