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

    Neuronpedia

    INDEX
    Explanations

    end of expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ちゃん
    0.36
     মিলে
    0.35
    ahid
    0.34
     बे
    0.34
    agro
    0.34
    OGRAM
    0.33
    ?.
    0.33
    ្នែក
    0.33
     hsize
    0.32
    Structured
    0.32
    POSITIVE LOGITS
    스와
    0.49
    と
    0.48
     Similarly
    0.47
     आणि
    0.46
     ਅਤੇ
    0.45
     και
    0.44
     있고
    0.44
     और
    0.43
     、
    0.43
     Likewise
    0.43
    Act Density 0.205%

    No Known Activations