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

    Neuronpedia

    INDEX
    Explanations

    seat belt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    öny
    -0.81
    갔
    -0.80
    attered
    -0.77
     súng
    -0.76
     کف
    -0.76
     引
    -0.75
    ționale
    -0.74
    ֳ
    -0.71
    carat
    -0.71
     "{{
    -0.71
    POSITIVE LOGITS
     seat
    1.98
     buckle
    1.77
     belt
    1.50
     Buckle
    1.48
     belted
    1.45
     Seat
    1.43
    seat
    1.41
     fastened
    1.36
     fasten
    1.36
    belt
    1.34
    Act Density 0.021%

    No Known Activations