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

    Neuronpedia

    INDEX
    Explanations

    'a' or 'A' followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    소
    0.62
     충
    0.61
    F
    0.59
    삼
    0.58
    -
    0.57
     Acqu
    0.57
    지
    0.57
     Principal
    0.57
    R
    0.56
     French
    0.55
    POSITIVE LOGITS
     বা
    1.00
     أو
    0.91
     či
    0.91
    或是
    0.89
    或
    0.89
     或
    0.87
     หรือ
    0.86
    或者
    0.81
     किंवा
    0.81
     или
    0.81
    Act Density 0.001%

    No Known Activations