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

    Neuronpedia

    INDEX
    Explanations

    costs, collection, waste, joint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.57
     territoire
    0.49
     deva
    0.49
     territory
    0.47
     arti
    0.45
     anga
    0.45
     mengandung
    0.44
    -
    0.44
     vasta
    0.43
     besar
    0.43
    POSITIVE LOGITS
     Од
    0.52
     ម
    0.50
    ብስ
    0.48
     परप
    0.46
    URNS
    0.45
    śred
    0.44
    点评
    0.43
    그램
    0.43
    ślin
    0.43
    ęb
    0.43
    Act Density 0.001%

    No Known Activations