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

    Neuronpedia

    INDEX
    Explanations

    connect to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ตัดสิน
    0.55
    யோ
    0.49
    决定
    0.47
    ສຸດ
    0.43
     উপায়
    0.43
     എന്റെ
    0.43
     결정
    0.43
     વિચ
    0.43
     sorprendente
    0.43
     همان
    0.42
    POSITIVE LOGITS
     been
    0.49
     motorists
    0.48
     fleets
    0.47
     wordt
    0.46
     calendar
    0.46
     temporadas
    0.45
     corporations
    0.45
     sejumlah
    0.45
     occurs
    0.45
     civilians
    0.44
    Act Density 0.003%

    No Known Activations