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

    Neuronpedia

    INDEX
    Explanations

    riddles about family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     after
    0.47
    شهاد
    0.40
    شه
    0.39
    باب
    0.37
     AFTER
    0.37
     blond
    0.37
     بعد
    0.36
    都市
    0.36
     After
    0.36
    ت
    0.36
    POSITIVE LOGITS
     пай
    0.41
     სისტ
    0.38
    níků
    0.37
    0.37
    itsa
    0.37
    laat
    0.37
    éget
    0.37
    虽
    0.37
    Device
    0.36
    anca
    0.36
    Act Density 0.001%

    No Known Activations