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

    Neuronpedia

    INDEX
    Explanations

    instances of opening and closing parentheses in code snippets

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

    add_ calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.62
    richTextPanel
    -0.60
    يميديا
    -0.59
    WindowConstants
    -0.57
    RegressionTest
    -0.56
    stdc
    -0.54
    AnimationsModule
    -0.49
    scriptcase
    -0.49
    ("'"
    -0.49
    ^(@
    -0.48
    POSITIVE LOGITS
     add
    0.93
     added
    0.91
     Add
    0.88
    Adding
    0.86
     adding
    0.86
    add
    0.84
     Adding
    0.84
     addition
    0.83
    added
    0.82
    Add
    0.81
    Act Density 0.015%

    No Known Activations