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

    Neuronpedia

    INDEX
    Explanations

    command line tools and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intention
    0.42
     ইচ্ছা
    0.37
     hele
    0.37
     SPR
    0.36
     भ
    0.36
     mere
    0.35
     dix
    0.35
    Ust
    0.35
     olmak
    0.34
     vorgesehen
    0.34
    POSITIVE LOGITS
     रै
    0.40
    გნ
    0.39
     চট্ট
    0.39
     бит
    0.39
    柣
    0.39
     ञ
    0.38
    лин
    0.38
    툐
    0.38
     realtor
    0.38
    一天
    0.38
    Act Density 0.038%

    No Known Activations