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

    Neuronpedia

    INDEX
    Explanations

    Reverence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     methyl
    -0.09
     ministra
    -0.08
     sever
    -0.08
     mime
    -0.08
     ministre
    -0.07
    irim
    -0.07
     poursu
    -0.07
     trygg
    -0.07
     ministère
    -0.07
     minist
    -0.07
    POSITIVE LOGITS
     सम्मान
    0.11
     awe
    0.11
     admiration
    0.11
     envers
    0.10
     尊
    0.10
     rever
    0.10
     appreciation
    0.09
    敬
    0.09
    尊
    0.09
     appreciative
    0.09
    Act Density 0.025%

    No Known Activations