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

    Neuronpedia

    INDEX
    Explanations

    therapists

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warehouse
    0.61
    део
    0.59
     Warehouse
    0.59
    warehouse
    0.58
    垟
    0.56
     подчер
    0.55
     ফার্ম
    0.55
     फार्
    0.54
     ophthalm
    0.54
    Warehouse
    0.54
    POSITIVE LOGITS
     skut
    0.62
    カタ
    0.62
     Catt
    0.55
     Kyrgyzstan
    0.55
    Viki
    0.55
     Cathy
    0.55
     forefathers
    0.54
     Jahrhundert
    0.54
     Gesetz
    0.53
     közvet
    0.52
    Act Density 0.001%

    No Known Activations