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

    Neuronpedia

    INDEX
    Explanations

    locations and technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thailand
    0.38
     takže
    0.38
     thailand
    0.38
     wsi
    0.38
     hong
    0.38
    یکشن
    0.38
     chúng
    0.37
     新
    0.37
     Australia
    0.37
     convuls
    0.37
    POSITIVE LOGITS
    ón
    0.44
     पर्यटकों
    0.42
    備
    0.41
    글
    0.41
     преимуще
    0.41
     עם
    0.40
    பந்த
    0.40
    筥
    0.39
    ė
    0.39
    쐞
    0.39
    Act Density 0.033%

    No Known Activations