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

    Neuronpedia

    INDEX
    Explanations

    programming code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hjust
    0.42
    Simpson
    0.41
     läk
    0.41
     स्लाइड
    0.39
     cz
    0.38
    textAlign
    0.37
    Slides
    0.36
     ç
    0.36
     Fransa
    0.36
     Ç
    0.36
    POSITIVE LOGITS
    erial
    0.44
    ref
    0.43
    感到
    0.42
    refs
    0.41
     पड़े
    0.41
    efficients
    0.39
     पड़ी
    0.39
    paying
    0.39
    posting
    0.39
    representing
    0.38
    Act Density 0.000%

    No Known Activations