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

    Neuronpedia

    INDEX
    Explanations

    for + category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginners
    1.91
     beginner
    1.76
     novices
    1.57
     novice
    1.57
     Beginners
    1.54
    beginner
    1.51
     Beginner
    1.48
    初心者
    1.47
     newbie
    1.39
     newbies
    1.38
    POSITIVE LOGITS
    food
    0.78
     love
    0.78
    Love
    0.76
    Food
    0.76
     Love
    0.74
     food
    0.73
     animal
    0.72
    love
    0.72
     lover
    0.70
    Loved
    0.70
    Act Density 0.019%

    No Known Activations