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

    Neuronpedia

    INDEX
    Explanations

    if not or no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архе
    0.41
     রেখেছেন
    0.41
    λλην
    0.41
     realmente
    0.39
     হওয়
    0.38
     PURCHASE
    0.38
     রেখেছে
    0.38
     ઘણી
    0.38
     souvent
    0.38
     Beziehung
    0.38
    POSITIVE LOGITS
     outright
    0.48
     则
    0.48
     find
    0.45
     esetén
    0.43
     fails
    0.41
    find
    0.40
     initial
    0.39
     wipers
    0.38
     或者
    0.37
     Allora
    0.37
    Act Density 0.065%

    No Known Activations