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

    Neuronpedia

    INDEX
    Explanations

    specifically isolating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attributing
    0.48
     blames
    0.47
     quaisquer
    0.46
     asserts
    0.45
     alleges
    0.44
     asserting
    0.44
     incul
    0.44
     estimates
    0.43
    erious
    0.43
    的他
    0.43
    POSITIVE LOGITS
    仪式
    0.50
     eternity
    0.48
    通话
    0.47
     pollination
    0.46
    Shipping
    0.46
     poetry
    0.45
    合物
    0.45
    чень
    0.45
    辐射
    0.45
    时间
    0.44
    Act Density 0.003%

    No Known Activations