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

    Neuronpedia

    INDEX
    Explanations

    micro, macro, and related names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    b
    1.06
    Б
    0.99
    ｂ
    0.96
    B
    0.93
    Բ
    0.90
     B
    0.90
     bith
    0.89
    Ｂ
    0.88
    Bai
    0.87
    ب
    0.86
    POSITIVE LOGITS
    Micro
    0.66
    mmas
    0.65
     Daven
    0.61
     micro
    0.59
    dis
    0.59
    Michael
    0.58
    <0xA0>
    0.58
     Micro
    0.58
    MAC
    0.57
     Mack
    0.57
    Act Density 0.193%

    No Known Activations