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

    Neuronpedia

    INDEX
    Explanations

    Explore and eat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     angel
    0.40
     zm
    0.40
    ᴏ
    0.38
     sed
    0.38
     angels
    0.38
     sign
    0.37
     malignancy
    0.37
     couch
    0.36
     chamber
    0.36
     whisper
    0.35
    POSITIVE LOGITS
    食事
    0.63
    食堂
    0.57
     Breakfast
    0.53
    Breakfast
    0.53
    饮食
    0.53
    Restaurants
    0.51
     ഭക്ഷണ
    0.50
    美食
    0.50
    meals
    0.49
    Meals
    0.48
    Act Density 0.025%

    No Known Activations