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

    Neuronpedia

    INDEX
    Explanations

    instructions after prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поиска
    0.43
     aquí
    0.42
     फीस
    0.41
     এখানে
    0.41
     यहाँ
    0.41
    ंडीगढ़
    0.40
    桃園
    0.40
     ее
    0.39
     avec
    0.39
    ស្ថាន
    0.38
    POSITIVE LOGITS
     realism
    0.40
     tomato
    0.40
     contrasted
    0.38
     asthma
    0.38
    spectrum
    0.38
     spectrum
    0.38
    ాలి
    0.37
    زش
    0.37
     oste
    0.37
     anti
    0.37
    Act Density 0.000%

    No Known Activations