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

    Neuronpedia

    INDEX
    Explanations

    unique cultural experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entiti
    0.35
    response
    0.34
    新たな
    0.34
    тивным
    0.34
     amd
    0.32
    ponential
    0.32
     submissions
    0.32
    populate
    0.32
     populate
    0.32
    UM
    0.32
    POSITIVE LOGITS
     Hotel
    0.34
     للح
    0.33
     بسي
    0.33
     Hôtel
    0.33
     Hotels
    0.32
     Ramón
    0.32
     lacked
    0.32
     Casa
    0.31
    滨
    0.31
    ši
    0.30
    Act Density 0.001%

    No Known Activations