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

    Neuronpedia

    INDEX
    Explanations

    README.md files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HTML
    0.52
     PHP
    0.50
    formatting
    0.44
    php
    0.43
     javascript
    0.43
    cite
    0.43
     formatting
    0.43
     html
    0.42
    代码
    0.42
    javascript
    0.41
    POSITIVE LOGITS
    Prevention
    0.42
    MD
    0.41
     MD
    0.40
    Luxury
    0.40
     rewritten
    0.39
    endaftaran
    0.39
     intrauterine
    0.38
     MDR
    0.38
    Written
    0.38
    MOND
    0.38
    Act Density 0.006%

    No Known Activations