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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.41
    est
    0.40
    ament
    0.36
    acht
    0.35
    ira
    0.33
    gle
    0.33
    resse
    0.33
    inia
    0.33
    ctions
    0.33
    nej
    0.33
    POSITIVE LOGITS
    깆
    0.39
    種類
    0.34
     знаем
    0.32
     astăzi
    0.32
    밂
    0.32
    ទំនាក់
    0.32
    知道
    0.31
    হাব
    0.31
    ၿ
    0.30
    ᱧ
    0.30
    Act Density 0.311%

    No Known Activations