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

    Neuronpedia

    INDEX
    Explanations

    these range from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tiên
    0.52
    FIND
    0.50
    ྪ
    0.49
    鬍
    0.49
     bestowed
    0.48
     ćel
    0.48
     predict
    0.48
     terceiro
    0.48
    ﺔ
    0.47
    噛
    0.47
    POSITIVE LOGITS
    د
    0.58
     Deutsch
    0.56
     عن
    0.55
     O
    0.54
    ر
    0.49
    ال
    0.48
     Blood
    0.46
     ن
    0.45
     VARCHAR
    0.45
    ش
    0.45
    Act Density 0.000%

    No Known Activations