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

    Neuronpedia

    INDEX
    Explanations

    non-English scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пикир
    0.49
    берриз
    0.47
    पाउंड
    0.45
    राबरी
    0.44
     oynuyoruz
    0.44
     delectable
    0.44
    नाल्ड
    0.43
    যানী
    0.43
    زمانہ
    0.43
     mullet
    0.43
    POSITIVE LOGITS
    ُ
    0.40
    力
    0.40
     آس
    0.38
    維
    0.38
    IM
    0.38
    .
    0.38
    有
    0.38
    出
    0.38
    人
    0.37
     在
    0.37
    Act Density 0.003%

    No Known Activations