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

    Neuronpedia

    INDEX
    Explanations

    numbers and division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.89
    و
    0.88
    at
    0.69
    Be
    0.68
    on
    0.68
    Map
    0.68
    Bingo
    0.67
    AE
    0.67
    ו
    0.66
    Foundation
    0.66
    POSITIVE LOGITS
    s
    0.93
     ต้อง
    0.73
    ยัง
    0.71
     โปร
    0.67
     过
    0.67
     eftersom
    0.66
     utilisent
    0.66
    asının
    0.66
    }/>
    0.65
    或者是
    0.65
    Act Density 0.026%

    No Known Activations