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

    Neuronpedia

    INDEX
    Explanations

    numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semi
    0.73
     Pit
    0.69
     labyrinth
    0.66
     DIY
    0.62
     further
    0.61
     Trans
    0.61
     multi
    0.60
     elegant
    0.60
     beaut
    0.59
     Beaut
    0.58
    POSITIVE LOGITS
     \\..
    0.92
    чением
    0.88
    是多少
    0.87
     ২
    0.86
    整数
    0.85
    洳
    0.84
    观众
    0.84
    atuan
    0.84
     शुरूआत
    0.84
     २
    0.83
    Act Density 0.471%

    No Known Activations