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

    Neuronpedia

    INDEX
    Explanations

    craft supplies, office supplies, objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ็ว
    0.52
     dagli
    0.47
     espejo
    0.46
    rição
    0.45
     destes
    0.45
     siendo
    0.42
     बच्चन
    0.41
    éri
    0.40
     acknow
    0.40
    कुंठ
    0.40
    POSITIVE LOGITS
    AUGUST
    0.45
    ्स
    0.44
    Điều
    0.44
    議員
    0.42
    leş
    0.41
    Bài
    0.41
    Means
    0.40
    lh
    0.40
    sched
    0.40
    Size
    0.40
    Act Density 0.005%

    No Known Activations