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

    Neuronpedia

    INDEX
    Explanations

    names and commentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Körper
    0.48
    కోండి
    0.46
     Бел
    0.45
     اسكت
    0.45
     Freighter
    0.44
    欬
    0.43
    Benzoimidazol
    0.43
     Demon
    0.42
     ἐν
    0.41
     અલ
    0.41
    POSITIVE LOGITS
     Huang
    0.46
     commentary
    0.46
    Huang
    0.45
     comment
    0.41
     solely
    0.41
    黃
    0.39
     comentario
    0.39
     黄
    0.39
    Cheng
    0.39
    comment
    0.38
    Act Density 0.001%

    No Known Activations