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

    Neuronpedia

    INDEX
    Explanations

    Indian proper nouns and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ví
    0.64
    setStyleSheet
    0.59
     የ
    0.54
     Zhuang
    0.54
     powerless
    0.53
     víz
    0.53
     Liao
    0.52
     ré
    0.52
     trai
    0.52
    보다
    0.52
    POSITIVE LOGITS
    olutely
    0.57
    arnas
    0.55
     Physiology
    0.55
    avatt
    0.55
     Pumps
    0.55
    Trailer
    0.54
     Leads
    0.53
     Acanth
    0.53
     Parse
    0.52
     Installation
    0.52
    Act Density 0.022%

    No Known Activations