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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related syntax

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

    hashing and validation of integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trekken
    -0.44
    +#+
    -0.41
    huriyet
    -0.40
     royaume
    -0.40
    CodedInputStream
    -0.39
     dezelve
    -0.39
    Royaume
    -0.39
     escuela
    -0.38
    HtmlAttribute
    -0.38
    `.`
    -0.37
    POSITIVE LOGITS
     '\\;'
    0.53
    Хьажоргаш
    0.52
     consultato
    0.48
    NoSuchAlgorithm
    0.48
     hashlib
    0.47
    MessageDigest
    0.44
    optionalTypeArgs
    0.42
    WithIOException
    0.41
    awtextra
    0.40
     CURIAM
    0.40
    Act Density 0.061%

    No Known Activations