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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structures in code samples

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

    programming source code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consist
    -0.42
     Inſ
    -0.38
     Conſ
    -0.38
     Reſ
    -0.37
     suff
    -0.37
     neceff
    -0.37
     fuper
    -0.36
     Anſ
    -0.35
     trick
    -0.35
     serve
    -0.34
    POSITIVE LOGITS
     ویکی‌پدی
    0.62
     Мексичка
    0.52
    RegressionTest
    0.50
    contentLoaded
    0.50
    MigrationBuilder
    0.49
    EndProject
    0.49
     GenerationType
    0.49
     Савезне
    0.48
     fieldNum
    0.48
    ########.
    0.48
    Act Density 0.020%

    No Known Activations