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

    Neuronpedia

    INDEX
    Explanations

    Delivery and inspection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conjunto
    -0.07
     Rank
    -0.07
     وراء
    -0.07
     сил
    -0.07
     derrière
    -0.07
    .rank
    -0.07
     rank
    -0.07
     cutting
    -0.07
    Firebase
    -0.07
     dominant
    -0.07
    POSITIVE LOGITS
     discrepancies
    0.14
     disputes
    0.13
     विवाद
    0.12
     dispute
    0.11
     discrep
    0.11
    _qty
    0.11
     disputed
    0.11
     অভিযোগ
    0.11
     disput
    0.10
     ரச
    0.10
    Act Density 0.049%

    No Known Activations