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

    Neuronpedia

    INDEX
    Explanations

    technical know-how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Knowledge
    0.55
     acknowledging
    0.51
    知识
    0.50
    knowledge
    0.49
     Knowledge
    0.48
     knowledge
    0.47
     acknowledge
    0.47
    NOWLEDGE
    0.46
     connaissance
    0.42
    acknowledge
    0.42
    POSITIVE LOGITS
    ハウ
    0.46
    Flair
    0.45
     Flair
    0.45
    expertise
    0.44
    鬏
    0.43
     Hao
    0.43
     ჰ
    0.39
     Transfers
    0.39
    侯
    0.39
     expertise
    0.39
    Act Density 0.001%

    No Known Activations