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

    Neuronpedia

    INDEX
    Explanations

    arrange objects or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.62
    ك
    0.57
    י
    0.57
    м
    0.53
    ни
    0.53
     персонал
    0.53
    ي
    0.53
    ת
    0.52
    ં
    0.51
    يا
    0.50
    POSITIVE LOGITS
     providing
    0.45
     Motor
    0.45
     Materials
    0.44
    works
    0.44
     barbeque
    0.44
    龙头
    0.43
     Film
    0.42
    wa
    0.42
    isely
    0.41
     That
    0.41
    Act Density 0.002%

    No Known Activations