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

    Neuronpedia

    INDEX
    Explanations

    on behalf of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.75
     или
    0.66
     atau
    0.64
     hoặc
    0.63
     లేదా
    0.63
     and
    0.61
     หรือ
    0.61
     या
    0.61
     ή
    0.60
    forums
    0.60
    POSITIVE LOGITS
    他の
    0.73
     altres
    0.73
     innych
    0.69
     daarbij
    0.68
     других
    0.65
     kajian
    0.64
     cursory
    0.63
     Kollegen
    0.63
     rappresent
    0.62
     diğer
    0.61
    Act Density 0.001%

    No Known Activations