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

    Neuronpedia

    INDEX
    Explanations

    MAC addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Morgan
    0.59
    Param
    0.58
    Jin
    0.55
    Leg
    0.53
    Same
    0.51
    Aden
    0.51
    Form
    0.50
    Russia
    0.50
    Back
    0.50
    Nau
    0.50
    POSITIVE LOGITS
     데이터
    0.63
     तालुक
    0.60
     elevados
    0.59
     것이
    0.57
     pelaksanaan
    0.56
     phường
    0.56
    ь
    0.56
     that
    0.56
    ีย
    0.55
     autoimmunity
    0.55
    Act Density 0.013%

    No Known Activations