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

    Neuronpedia

    INDEX
    Explanations

    Python syntax and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shareholders
    0.47
    eté
    0.44
     palavra
    0.43
    훌
    0.42
     triple
    0.40
     mutta
    0.40
     vaikka
    0.40
    이지만
    0.39
    работка
    0.39
     but
    0.38
    POSITIVE LOGITS
    Gan
    0.44
    0.44
     EVENT
    0.44
     ଓ
    0.43
    Despatx
    0.43
     ಕರಿಬೇವಿನ
    0.43
    ᱠ
    0.43
    London
    0.40
    Richardson
    0.40
    🧥
    0.40
    Act Density 0.009%

    No Known Activations