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

    Neuronpedia

    INDEX
    Explanations

    network analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     описа
    0.50
     distr
    0.46
     centrif
    0.46
     бан
    0.45
     поми
    0.45
     ejecut
    0.42
    ಡುಗೆ
    0.42
     ingred
    0.41
     وصف
    0.41
     inci
    0.41
    POSITIVE LOGITS
    7
    0.48
    wat
    0.48
    MOT
    0.48
    8
    0.47
    esses
    0.46
    THRESHOLD
    0.46
    rieb
    0.45
    ̀m
    0.45
    ş
    0.45
     म्हणजेच
    0.44
    Act Density 0.001%

    No Known Activations