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

    Neuronpedia

    INDEX
    Explanations

    leading a change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뮈
    0.47
    messer
    0.43
    ladies
    0.41
     વિદ્ય
    0.40
     intermédiaire
    0.38
     министер
    0.38
     হোমিওপ্যাথ
    0.38
    業界
    0.38
     эфи
    0.38
    IndexPath
    0.38
    POSITIVE LOGITS
     contrast
    0.45
    ,
    0.43
     cards
    0.41
     science
    0.40
     regards
    0.40
    cards
    0.39
     ed
    0.38
     digital
    0.38
     om
    0.38
    调
    0.38
    Act Density 0.000%

    No Known Activations