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

    Neuronpedia

    INDEX
    Explanations

    reviews of places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pathogenesis
    0.38
     narrative
    0.35
     ως
    0.35
     herein
    0.35
    罹
    0.34
     crucial
    0.34
     biomarker
    0.33
     transformar
    0.33
     transformative
    0.33
     authorship
    0.33
    POSITIVE LOGITS
    hotel
    0.43
     bagus
    0.42
     mooie
    0.42
    ホテル
    0.42
     mooi
    0.39
     вечером
    0.39
     nice
    0.39
     güzel
    0.39
    値段
    0.39
    素敵な
    0.39
    Act Density 0.004%

    No Known Activations