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

    Neuronpedia

    INDEX
    Explanations

    Is there anything to discuss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    价比
    0.70
     Compared
    0.70
    عار
    0.69
     Alten
    0.68
    TAGE
    0.65
    侕
    0.64
     Attitudes
    0.64
    ڕ
    0.62
    ılara
    0.62
    ⌵
    0.62
    POSITIVE LOGITS
     assist
    0.77
    зидент
    0.77
     perish
    0.75
     perch
    0.74
     обита
    0.72
     fotografía
    0.71
     hoop
    0.68
     assistance
    0.68
     prevent
    0.67
    nast
    0.66
    Act Density 0.093%

    No Known Activations