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

    Neuronpedia

    INDEX
    Explanations

    introducing examples or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    2.87
     anno
    2.66
     Stelle
    2.66
    গ্রাম
    2.56
     exacerb
    2.49
    郎
    2.48
    aded
    2.42
     nokta
    2.35
    Miscellaneous
    2.29
    ſt
    2.29
    POSITIVE LOGITS
    তে
    3.27
    os
    3.01
    ل
    2.88
    cid
    2.80
    ない
    2.78
     ndị
    2.67
    व
    2.65
    te
    2.65
    al
    2.50
     تعالى
    2.49
    Act Density 0.002%

    No Known Activations