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

    Neuronpedia

    INDEX
    Explanations

    Make sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    తంగా
    0.68
    وب
    0.67
     알아보
    0.66
    안녕하세요
    0.65
    ogon
    0.65
    쟁
    0.65
    സ്ഥാന
    0.64
     রক্ষ
    0.63
     Lạt
    0.63
    ⎞
    0.62
    POSITIVE LOGITS
     sure
    3.77
    sure
    3.15
     Sure
    3.13
    Sure
    3.09
     SURE
    2.85
     certain
    2.64
    certain
    2.61
     certainty
    2.60
     Certain
    2.55
    Certain
    2.53
    Act Density 0.255%

    No Known Activations