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

    Neuronpedia

    INDEX
    Explanations

    because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.43
    ccedil
    0.41
     invertir
    0.41
     investir
    0.40
     emblematic
    0.39
     prosp
    0.39
     earners
    0.39
     الح
    0.39
     expropri
    0.39
     peers
    0.39
    POSITIVE LOGITS
    因为
    0.57
     Çünkü
    0.55
    because
    0.55
     çünkü
    0.55
     γιατί
    0.55
     BECAUSE
    0.55
     Because
    0.54
    因為
    0.54
     omdat
    0.53
     因為
    0.53
    Act Density 0.000%

    No Known Activations