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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iniu
    0.49
    ط
    0.49
    ص
    0.48
     N
    0.47
    тено
    0.46
    ιου
    0.44
    طاء
    0.44
     Darth
    0.44
    ião
    0.43
     ImageView
    0.43
    POSITIVE LOGITS
     drove
    0.53
    コミュニ
    0.50
     ಕಳೆದ
    0.50
    ೧
    0.49
     हैन
    0.47
     paymentRequest
    0.46
     ಆದರೆ
    0.46
     strCmd
    0.45
     ಖರೀ
    0.45
    呉
    0.45
    Act Density 0.001%

    No Known Activations