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

    Neuronpedia

    INDEX
    Explanations

    power dynamics and complex themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     storie
    0.84
     episodio
    0.71
     épisode
    0.70
     cerita
    0.70
     woorden
    0.68
    證據
    0.66
     Episode
    0.66
    故事
    0.66
    厚的
    0.65
    rians
    0.65
    POSITIVE LOGITS
     dynamic
    1.91
     Dynamic
    1.69
    dynamic
    1.68
    Dynamic
    1.65
    动态
    1.41
     динами
    1.40
     dynam
    1.36
     dynamics
    1.36
     dynamique
    1.26
     dinam
    1.25
    Act Density 0.471%

    No Known Activations