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

    Neuronpedia

    INDEX
    Explanations

    examples, video, plays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fireworks
    0.44
     buhay
    0.44
     hates
    0.41
    ອງ
    0.40
     Typography
    0.40
    iffany
    0.40
     Finals
    0.39
     Prep
    0.39
     क्योंकि
    0.38
     Farewell
    0.38
    POSITIVE LOGITS
    ibusdam
    0.44
    ellä
    0.41
    updating
    0.41
    ACTION
    0.40
    對
    0.40
    ’
    0.39
     cereals
    0.39
    な
    0.39
     steps
    0.38
     ମ
    0.38
    Act Density 0.000%

    No Known Activations