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

    Neuronpedia

    INDEX
    Explanations

    connective words and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     persists
    0.52
     exponentially
    0.48
     দ্বিতীয়
    0.45
     hospitalized
    0.44
     panorama
    0.44
    電流
    0.44
     വീഡിയോ
    0.43
     пребы
    0.43
    rectangular
    0.43
     পুষ
    0.43
    POSITIVE LOGITS
    어를
    0.52
    язку
    0.49
    여
    0.46
    থা
    0.43
    یا
    0.42
     moim
    0.41
    ሐ
    0.41
    ците
    0.40
    3
    0.40
    شنا
    0.40
    Act Density 0.005%

    No Known Activations