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

    Neuronpedia

    INDEX
    Explanations

    clothing and fabrics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ibu
    0.87
    Taxi
    0.77
     Glucose
    0.76
    Vocabulary
    0.76
    Grilled
    0.76
     Güzel
    0.75
     Grilled
    0.74
    Neigh
    0.73
    Butterfly
    0.73
    ায়া
    0.72
    POSITIVE LOGITS
     فهو
    0.66
    مد
    0.65
     RID
    0.63
    pag
    0.62
     انتخابات
    0.62
    9
    0.62
    3
    0.62
    全く
    0.61
     respects
    0.60
    নির্বাচ
    0.60
    Act Density 0.000%

    No Known Activations