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

    Neuronpedia

    INDEX
    Explanations

    real, real-time, realistic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affirmatively
    0.80
     عفوا
    0.65
    جور
    0.65
     unequivocally
    0.62
    孜
    0.59
     explicitly
    0.59
    蕴
    0.58
    omination
    0.58
    oción
    0.57
    ౪
    0.57
    POSITIVE LOGITS
     real
    5.63
    Real
    5.41
     Real
    5.36
    real
    5.23
     REAL
    4.54
    REAL
    4.54
     реа
    4.12
     रियल
    4.02
    リアル
    3.89
    现实
    3.87
    Act Density 0.710%

    No Known Activations