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

    Neuronpedia

    INDEX
    Explanations

    terms related to encryption and cryptographic methods

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

    codes and secrecy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.39
    RectangleBorder
    -0.37
    ppelin
    -0.36
    ieke
    -0.34
    ="@+
    -0.34
    мку
    -0.34
     "..\..\
    -0.34
     antaranya
    -0.33
    rem
    -0.33
    risch
    -0.31
    POSITIVE LOGITS
     ویکی‌پدی
    0.65
    AndEndTag
    0.54
    postIndex
    0.53
     الحره
    0.52
     utafitiHapana
    0.50
    lgari
    0.50
     '\\;'
    0.49
    tagHelperRunner
    0.48
     propOrder
    0.48
     مرئيه
    0.48
    Act Density 0.158%

    No Known Activations