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

    Neuronpedia

    INDEX
    Explanations

    data structures and their components, particularly regarding programming and technical specifications

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

    Code, mathematics, and technical language

    np_acts-logits-general · gemini-2.0-flash

    code and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.34
     дописавши
    -1.33
     '\\;'
    -1.29
     فريبيس
    -1.24
    writeFieldEnd
    -1.23
     للاسماء
    -1.22
    RenderAtEndOf
    -1.20
    "]);
    -1.15
    DockStyle
    -1.14
     Мексичка
    -1.10
    POSITIVE LOGITS
     
    0.67
    </strong>
    0.64
    ,
    0.62
     (
    0.61
    ↵
    0.58
    '
    0.58
    ...
    0.57
      
    0.56
    .
    0.56
    -
    0.56
    Act Density 2.853%

    No Known Activations