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

    Neuronpedia

    INDEX
    Explanations

    foreign words or characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inter
    0.40
     làm
    0.40
     lima
    0.38
     dei
    0.38
     Sept
    0.37
     description
    0.37
     gén
    0.37
     Inter
    0.37
     September
    0.37
     economical
    0.37
    POSITIVE LOGITS
     아니고
    0.43
    ورسٹی
    0.43
    මණ
    0.43
    வாய்
    0.43
     буди
    0.41
    액
    0.41
    ىسى
    0.41
    벗
    0.41
    ⿶
    0.41
    हेलो
    0.41
    Act Density 0.000%

    No Known Activations