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

    Neuronpedia

    INDEX
    Explanations

    multilingual descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immediate
    0.39
     collaboration
    0.39
    OMIC
    0.39
     transformation
    0.39
    Liter
    0.38
     literal
    0.38
     collaborative
    0.38
    planting
    0.38
     emphatically
    0.38
    REEN
    0.37
    POSITIVE LOGITS
    क्रो
    0.44
     siang
    0.41
     psicología
    0.39
     ক্রি
    0.38
     Cramer
    0.38
     बाप
    0.38
    最適な
    0.38
    আমর
    0.37
     safari
    0.36
     apakah
    0.36
    Act Density 0.001%

    No Known Activations