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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⴻ
    0.45
     fam
    0.42
     geben
    0.41
     enige
    0.40
    leck
    0.40
     reina
    0.40
     charms
    0.39
     finner
    0.39
     eux
    0.39
    fam
    0.39
    POSITIVE LOGITS
    ↵↵↵↵
    0.45
    ↵↵
    0.43
     जिलाधिकारी
    0.39
    worthiness
    0.38
     これらの
    0.37
     ہوں۔
    0.37
     While
    0.36
     ஆகிய
    0.36
    😓
    0.36
     असाल
    0.35
    Act Density 0.133%

    No Known Activations