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

    Neuronpedia

    INDEX
    Explanations

    short answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smallskip
    0.42
     灬
    0.39
    aldehyde
    0.39
     элементов
    0.39
    0.38
    âncias
    0.38
    \},\
    0.38
    <unused9>
    0.37
    র্ব
    0.37
    entropic
    0.36
    POSITIVE LOGITS
     summary
    0.53
    結論
    0.52
     skips
    0.46
     Summary
    0.45
    قبل
    0.44
     recommendation
    0.44
    まとめ
    0.44
     before
    0.43
     خلص
    0.43
    Summary
    0.42
    Act Density 0.239%

    No Known Activations