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

    Neuronpedia

    INDEX
    Explanations

    increment and decrement operations in code

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

    incrementing code loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ={
    -0.48
    SDR
    -0.43
    //};
    -0.42
     SDR
    -0.42
    Belf
    -0.42
    //{
    -0.40
    ":
    -0.40
    harmed
    -0.40
    csname
    -0.39
    >';
    -0.39
    POSITIVE LOGITS
     ++
    2.16
    ;++
    1.45
     (++
    1.23
    (++
    1.13
     ++)
    1.13
    [++
    1.05
    ++
    0.96
     +++
    0.91
     ++;
    0.88
    ++$
    0.88
    Act Density 0.005%

    No Known Activations