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

    Neuronpedia

    INDEX
    Explanations

    numbers and money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อาด
    0.65
     vucc
    0.61
    urrent
    0.60
    밉
    0.59
    orni
    0.59
     genau
    0.59
     való
    0.59
    databind
    0.59
    avlja
    0.59
    ㅢ
    0.59
    POSITIVE LOGITS
    5
    1.56
    8
    1.45
    7
    1.23
    2
    1.22
    6
    1.15
    3
    1.06
    4
    0.99
    ۵
    0.98
    ５
    0.95
    ៥
    0.91
    Act Density 0.260%

    No Known Activations