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

    Neuronpedia

    INDEX
    Explanations

    Amazon services and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.82
    在
    0.67
    0.67
    你
    0.65
     في
    0.62
    د
    0.61
    我们
    0.61
     س
    0.57
    piano
    0.57
    p
    0.55
    POSITIVE LOGITS
     позволяют
    0.64
    स्पून
    0.59
    েল
    0.59
    стаў
    0.57
     સરળ
    0.57
    ින්
    0.56
    ִי
    0.56
    婧
    0.56
    Ꮑ
    0.55
    দায়
    0.55
    Act Density 0.006%

    No Known Activations