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

    Neuronpedia

    INDEX
    Explanations

    business and health

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    پاکستان
    0.61
    ablemente
    0.60
    Seine
    0.57
    อย่าง
    0.56
    챱
    0.53
     반지름
    0.53
    ပြည်
    0.52
    inaan
    0.52
    冷蔵
    0.52
    hti
    0.51
    POSITIVE LOGITS
    ുക
    0.61
     Crossing
    0.57
     TUB
    0.57
     Stay
    0.56
     CONTACT
    0.56
     runners
    0.55
     Treasurer
    0.55
     sulfon
    0.55
     टू
    0.54
     সান
    0.54
    Act Density 0.000%

    No Known Activations