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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related actions, particularly focusing on writing and implementing functions and procedures

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

    writing code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.47
     ویکی‌پدی
    -0.40
    シャ
    -0.38
     blank
    -0.38
    Personensuche
    -0.37
    ams
    -0.35
     arrive
    -0.35
    blank
    -0.34
     endless
    -0.34
     AIAA
    -0.33
    POSITIVE LOGITS
    GEBURTSDATUM
    0.64
     Written
    0.56
    __':
    0.55
    Written
    0.55
    编写
    0.55
    numerusform
    0.52
     Wrote
    0.52
     ontwikkel
    0.51
    written
    0.51
     written
    0.50
    Act Density 0.099%

    No Known Activations