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

    Neuronpedia

    INDEX
    Explanations

    software, programming, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sized
    0.78
    approx
    0.77
    circa
    0.76
    ksjon
    0.75
    (
    0.74
     mentre
    0.71
    لي
    0.69
    tumor
    0.69
    sink
    0.68
    iskt
    0.68
    POSITIVE LOGITS
     afar
    0.78
    সাধারণ
    0.77
    ྒྱ
    0.73
     acclaimed
    0.72
     Peas
    0.71
     Software
    0.71
     visionary
    0.71
     Sketches
    0.71
     বিক্রয়
    0.70
     aptly
    0.68
    Act Density 0.000%

    No Known Activations