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

    Neuronpedia

    INDEX
    Explanations

    project manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     první
    0.45
    的状态
    0.42
    átor
    0.41
    ँकि
    0.39
    ндары
    0.39
    的名
    0.39
     днів
    0.39
     cig
    0.39
    rugu
    0.38
     厚
    0.38
    POSITIVE LOGITS
    ول
    0.48
    الب
    0.47
    ל
    0.45
    ול
    0.43
    日本の
    0.43
    Hitting
    0.43
    妧
    0.42
    خ
    0.42
    ות
    0.42
     gestion
    0.42
    Act Density 0.027%

    No Known Activations