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

    Neuronpedia

    INDEX
    Explanations

    Important considerations and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۇر
    0.45
     simili
    0.41
     alo
    0.41
     autrement
    0.40
     osse
    0.40
    ्ट
    0.40
     allemande
    0.40
     portugu
    0.39
     corrispond
    0.39
     tedesco
    0.39
    POSITIVE LOGITS
     Principles
    0.56
    Principles
    0.52
     Grundlagen
    0.51
    principles
    0.50
    Basic
    0.47
    Disclaimer
    0.47
    basic
    0.47
     मूलभूत
    0.46
     बुनियादी
    0.46
     Basic
    0.45
    Act Density 0.110%

    No Known Activations