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

    Neuronpedia

    INDEX
    Explanations

    data related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waxing
    0.44
    كات
    0.44
     ticketing
    0.43
     trouver
    0.40
     denomination
    0.40
    رو
    0.40
    ками
    0.39
    玹
    0.39
    ელ
    0.38
    ဝ
    0.38
    POSITIVE LOGITS
     getData
    0.65
    flow
    0.63
     osobow
    0.59
     GetData
    0.59
     प्रोसेसिंग
    0.57
    a
    0.57
     setData
    0.54
    सेट
    0.52
     streams
    0.52
     ObjData
    0.52
    Act Density 0.107%

    No Known Activations