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

    Neuronpedia

    INDEX
    Explanations

    br / Br

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حيث
    0.39
    お店
    0.38
    reachable
    0.38
    ग्रहण
    0.38
    粵
    0.38
    鉀
    0.38
    viving
    0.37
     সাধারণভাবে
    0.36
    ىم
    0.36
     ऑलरेडी
    0.36
    POSITIVE LOGITS
     br
    0.93
     Br
    0.91
     BR
    0.86
    Br
    0.79
     brach
    0.77
     ब्र
    0.76
     Бри
    0.75
     бра
    0.73
     Bragg
    0.72
     브
    0.71
    Act Density 0.022%

    No Known Activations