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

    Neuronpedia

    INDEX
    Explanations

    g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अवधारणा
    0.56
    众人
    0.55
    理念
    0.52
     시절
    0.48
    อย่างไร
    0.48
    প্রতিষ্ঠ
    0.48
    法则
    0.48
     spôsob
    0.48
    Concept
    0.46
     sekaligus
    0.46
    POSITIVE LOGITS
     x
    0.62
     D
    0.61
     P
    0.59
     T
    0.58
     X
    0.58
     F
    0.56
     Վ
    0.55
     tiga
    0.54
     B
    0.54
     XRD
    0.53
    Act Density 0.781%

    No Known Activations