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

    Neuronpedia

    INDEX
    Explanations

    business and law

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caliper
    0.66
     Elias
    0.62
     Damien
    0.61
    রোপ
    0.59
     dismissing
    0.58
    اويه
    0.56
     Episode
    0.55
    िल्ली
    0.55
     meats
    0.55
     HPE
    0.55
    POSITIVE LOGITS
    urón
    0.66
    しくは
    0.63
     '<
    0.61
     próp
    0.60
    िशन
    0.57
    bq
    0.57
     ripar
    0.57
    ترنت
    0.55
    ずに
    0.54
    ('<
    0.54
    Act Density 0.000%

    No Known Activations