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

    Neuronpedia

    INDEX
    Explanations

    visual image creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অন্যান্য
    0.55
    Other
    0.43
     بیشتر
    0.43
    :
    0.40
    ,
    0.40
    *
    0.39
    或其他
    0.39
     (
    0.38
     અથવા
    0.38
                    
    0.37
    POSITIVE LOGITS
    ᆯ
    0.46
     คลิ
    0.45
    र्यंत
    0.45
    之时
    0.44
     любовь
    0.43
    未來
    0.42
     março
    0.42
    כה
    0.41
     મોત
    0.41
     עד
    0.41
    Act Density 0.007%

    No Known Activations