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

    Neuronpedia

    INDEX
    Explanations

    postal codes and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presentation
    0.42
     régionale
    0.42
     former
    0.41
     learnings
    0.40
    ALLED
    0.39
     jeunes
    0.39
     appelé
    0.39
     chamado
    0.38
     de
    0.38
    former
    0.38
    POSITIVE LOGITS
    ᱐
    0.45
    ΙΑ
    0.44
    咊
    0.44
     ܠ
    0.43
    儅
    0.43
    ವಿಲ್ಲ
    0.41
    秏
    0.41
    َان
    0.41
    ਿਕ
    0.40
     ಮನೆ
    0.40
    Act Density 0.001%

    No Known Activations