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

    Neuronpedia

    INDEX
    Explanations

    code snippet structure in programming languages

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

    Hexadecimal values with a leading "0x"

    np_acts-logits-general · gemini-2.0-flash

    functions useful for analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.70
    ########.
    -0.63
     فريبيس
    -0.60
    CppCodeGen
    -0.59
    UserScript
    -0.57
     isempty
    -0.57
    MarshalTo
    -0.56
    LEncoder
    -0.56
    Portale
    -0.56
    QMetaType
    -0.56
    POSITIVE LOGITS
     fût
    0.63
    Autoritní
    0.57
     colectiva
    0.56
     aisladas
    0.56
    grenze
    0.55
     ansik
    0.54
    eseorang
    0.52
    
    0.52
    berdayakan
    0.52
     malheure
    0.51
    Act Density 0.066%

    No Known Activations