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

    Neuronpedia

    INDEX
    Explanations

    explaining or clarifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሁሉም
    0.52
     volled
    0.50
    դ
    0.49
     Дата
    0.48
     млрд
    0.48
     effettu
    0.48
     ಎಲ್ಲಾ
    0.48
     ಉತ್ಪ
    0.48
    ាល
    0.47
    ۲۰
    0.47
    POSITIVE LOGITS
     TF
    0.42
    ↵↵
    0.41
     cements
    0.40
     Axial
    0.40
    (
    0.40
     AMA
    0.40
     Ramón
    0.40
    éticas
    0.39
     nanof
    0.38
     puts
    0.38
    Act Density 0.005%

    No Known Activations