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

    Neuronpedia

    INDEX
    Explanations

    negative consequences and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     یا
    0.55
     یک
    0.51
     một
    0.50
    cię
    0.49
    某个
    0.48
     या
    0.47
    这个
    0.47
    电视
    0.46
     façon
    0.46
     Tired
    0.46
    POSITIVE LOGITS
     casualties
    0.46
     diffusion
    0.45
     fatalities
    0.43
     proliferation
    0.42
    ORG
    0.42
    IN
    0.41
    GDP
    0.41
     ಜೀವ
    0.40
     contagion
    0.40
    NATO
    0.40
    Act Density 0.002%

    No Known Activations