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

    Neuronpedia

    INDEX
    Explanations

    elements of programming or file structure

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

    code and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.56
    awtextra
    -0.51
    fjspx
    -0.46
    MessageTagHelper
    -0.45
     yyq
    -0.43
     الرياضيه
    -0.43
    autaire
    -0.43
     EClass
    -0.40
    úsqueda
    -0.40
    tangentMode
    -0.40
    POSITIVE LOGITS
    styleType
    0.54
     CommonModule
    0.49
    تقاوى
    0.47
     صوتيه
    0.47
     autorytatywna
    0.45
     wireType
    0.45
    +#+#
    0.45
     formales
    0.44
    moduleId
    0.44
    WireFormatLite
    0.43
    Act Density 0.000%

    No Known Activations