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

    Neuronpedia

    INDEX
    Explanations

    data structures and elements related to programming concepts

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

    Code containing device names

    np_acts-logits-general · gemini-2.0-flash

    code tokens ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *{
    -0.32
     tug
    -0.30
     fight
    -0.28
     partnership
    -0.28
     respon
    -0.28
     defer
    -0.28
    cend
    -0.27
     cog
    -0.27
     valid
    -0.26
    HashCode
    -0.26
    POSITIVE LOGITS
     betweenstory
    1.04
    UVWXYZ
    0.80
    parsedMessage
    0.79
    GEBURTSDATUM
    0.74
    Portály
    0.71
    ⤹
    0.70
    MigrationBuilder
    0.70
    WebElementEntity
    0.69
    CppMethod
    0.66
    enderror
    0.65
    Act Density 0.088%

    No Known Activations