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

    Neuronpedia

    INDEX
    Explanations

    * crucial / important words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pancakes
    0.39
    .
    0.37
     і
    0.37
     revolves
    0.37
     a
    0.36
     involves
    0.35
     interferes
    0.35
     the
    0.35
            
    0.34
     ї
    0.34
    POSITIVE LOGITS
     также
    0.42
     Также
    0.40
     ønsker
    0.40
     także
    0.40
     також
    0.40
     кеңсеси
    0.39
     tentunya
    0.39
     Chúng
    0.38
     također
    0.38
     Такие
    0.38
    Act Density 0.000%

    No Known Activations