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

    Neuronpedia

    INDEX
    Explanations

    country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    χη
    0.39
    state
    0.38
    NC
    0.36
    щите
    0.35
    টাই
    0.35
    teaser
    0.35
    itr
    0.34
     doctr
    0.34
    除
    0.33
    렵
    0.33
    POSITIVE LOGITS
     yil
    0.48
     शहर
    0.42
     otherworldly
    0.42
     Daha
    0.41
     cloths
    0.41
     ~(~)
    0.40
     العالمية
    0.40
     Kowloon
    0.40
    世界上最大的
    0.40
     മ
    0.40
    Act Density 0.003%

    No Known Activations