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

    Neuronpedia

    INDEX
    Explanations

    lists and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arlo
    0.47
     antics
    0.46
    Prince
    0.45
    区域
    0.45
    לו
    0.45
     شباب
    0.45
    材质
    0.45
    楼
    0.45
    桡
    0.45
     প্রিন
    0.44
    POSITIVE LOGITS
     с
    0.56
     слова
    0.44
    with
    0.44
     таким
    0.42
     в
    0.42
    preserving
    0.40
     дороги
    0.40
     LETTERS
    0.40
    $-[
    0.40
     затем
    0.39
    Act Density 0.001%

    No Known Activations