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

    Neuronpedia

    INDEX
    Explanations

    what you prefer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceedings
    0.80
    ocumented
    0.72
    ्मण
    0.71
     ilegal
    0.71
     экзем
    0.70
     ಪ್ರಕರಣ
    0.69
     കേസ
    0.69
     സെക്രട്ട
    0.67
    stats
    0.67
     നടപ
    0.66
    POSITIVE LOGITS
     preferences
    1.45
     preference
    1.44
     Preference
    1.28
     Preferences
    1.28
    preference
    1.22
    preferences
    1.19
     preferred
    1.13
     prefers
    1.12
     favorite
    1.11
    喜欢
    1.08
    Act Density 1.060%

    No Known Activations