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

    Neuronpedia

    INDEX
    Explanations

    add ingredients until combined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を使う
    0.33
    ریق
    0.29
    睡眠
    0.29
     Insulation
    0.29
     ئە
    0.28
     osteoporosis
    0.28
     Creme
    0.27
    removeFrom
    0.27
    готовить
    0.27
    を使った
    0.27
    POSITIVE LOGITS
     gently
    0.37
     continue
    0.30
     immediately
    0.28
     quickly
    0.28
    point
    0.28
     remaining
    0.28
     slightly
    0.27
     brisk
    0.27
     Continue
    0.27
     aż
    0.27
    Act Density 0.082%

    No Known Activations