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

    Neuronpedia

    INDEX
    Explanations

    airport arrival locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legislature
    0.49
     аўта
    0.48
     चुप
    0.47
     प्रतिनिधि
    0.47
     silenc
    0.47
     tablero
    0.46
    рита
    0.45
     també
    0.44
    シリ
    0.44
     द्वारा
    0.43
    POSITIVE LOGITS
    la
    0.42
    Gamma
    0.42
     thrills
    0.41
     Sets
    0.39
     Qualification
    0.38
    搬
    0.38
     Skills
    0.38
    5
    0.37
    لاق
    0.37
    peng
    0.37
    Act Density 0.004%

    No Known Activations