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

    Neuronpedia

    INDEX
    Explanations

    Gemma AI model link

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மீ
    0.43
     DHT
    0.41
    bros
    0.40
     dhamma
    0.38
    bowtie
    0.38
     жо
    0.37
     sms
    0.37
     এডিনবার্গ
    0.36
    鑊
    0.36
    っいて
    0.36
    POSITIVE LOGITS
     Cloud
    0.45
     cloud
    0.43
    Cloud
    0.42
    Claude
    0.40
    cloud
    0.39
    クラウド
    0.39
     Kill
    0.38
     Bl
    0.38
    Gem
    0.37
     Ap
    0.37
    Act Density 0.010%

    No Known Activations