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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IAEA
    0.53
     Несмотря
    0.49
    서울특별시
    0.48
     Greenpeace
    0.46
     සැල
    0.46
     Mumbai
    0.46
    新型コロナ
    0.46
     HSPB
    0.46
     ಮಂಗಳ
    0.45
     UNICEF
    0.44
    POSITIVE LOGITS
    ība
    0.44
     cast
    0.42
    ības
    0.42
    !
    0.41
     friends
    0.41
     left
    0.40
    ly
    0.40
     jones
    0.39
    ine
    0.39
    il
    0.38
    Act Density 0.000%

    No Known Activations