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

    Neuronpedia

    INDEX
    Explanations

    academic databases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     filtro
    0.42
     বিজে
    0.40
     रैंकिंग
    0.40
    තිය
    0.39
    nections
    0.38
     analytic
    0.38
    яна
    0.38
    排名
    0.37
    コーヒー
    0.37
     इंटीग्रेशन
    0.37
    POSITIVE LOGITS
     grey
    0.51
     Grey
    0.48
     Gray
    0.44
    Grey
    0.43
     gray
    0.43
    grey
    0.42
     putih
    0.42
    灰
    0.40
     Channel
    0.40
     Dawn
    0.38
    Act Density 0.007%

    No Known Activations