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

    Neuronpedia

    INDEX
    Explanations

    pytorch neural network imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     X
    0.42
    ิ่ง
    0.42
     H
    0.41
     Color
    0.40
    0
    0.40
     T
    0.39
     halluc
    0.38
     J
    0.38
     MS
    0.37
    tól
    0.37
    POSITIVE LOGITS
    برای
    0.47
    heast
    0.45
     dla
    0.45
    ط
    0.44
    สำหรับ
    0.43
    जल
    0.42
    heal
    0.42
     लिए
    0.42
    점으로
    0.42
    ouvrage
    0.41
    Act Density 0.009%

    No Known Activations