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

    Neuronpedia

    INDEX
    Explanations

    up and down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     සහ
    0.43
    và
    0.37
     cuyas
    0.37
     الذين
    0.36
     которые
    0.36
     وقد
    0.36
    और
    0.36
     다섯
    0.36
     جديدة
    0.35
     தொடங்கி
    0.35
    POSITIVE LOGITS
    只是
    0.35
    有用
    0.35
     yourself
    0.33
    ิน
    0.32
     ở
    0.32
     kiệm
    0.32
     enjoyment
    0.31
    的时候
    0.31
    的机会
    0.31
     satiety
    0.31
    Act Density 0.000%

    No Known Activations