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

    Neuronpedia

    INDEX
    Explanations

    medical or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continental
    0.39
     doors
    0.37
     perpetuate
    0.36
     profusely
    0.35
    ବା
    0.35
     sleepless
    0.34
     blocks
    0.34
    anjutnya
    0.34
     lines
    0.34
     dro
    0.34
    POSITIVE LOGITS
    的公司
    0.44
    的企业
    0.43
    ferred
    0.42
    未知
    0.42
    不想
    0.41
    ферен
    0.40
    yzed
    0.39
    양이
    0.39
     Harwell
    0.39
    гон
    0.38
    Act Density 0.000%

    No Known Activations