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

    Neuronpedia

    INDEX
    Explanations

    coax stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.46
    ース
    0.45
     leadership
    0.43
    ᠰ
    0.43
    스트
    0.42
    ىلى
    0.42
     capital
    0.42
    աստ
    0.42
    ﺿ
    0.41
    ād
    0.40
    POSITIVE LOGITS
     merveille
    0.51
     bril
    0.49
     kompon
    0.47
    houette
    0.46
    silhouette
    0.46
     familien
    0.46
    អារ
    0.46
     اوقات
    0.45
     पैनल
    0.45
     lồ
    0.45
    Act Density 0.004%

    No Known Activations