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

    Neuronpedia

    INDEX
    Explanations

    parentheses and quotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     United
    0.31
     Zan
    0.29
     Mathieu
    0.29
     compat
    0.29
     Norway
    0.28
    截图
    0.28
     whatsoever
    0.28
     observability
    0.27
    ərb
    0.27
     ইসলাম
    0.27
    POSITIVE LOGITS
     offend
    0.35
     بن
    0.33
     नाटक
    0.33
     ejercer
    0.33
     betont
    0.32
     게
    0.32
     scheint
    0.32
    teile
    0.31
     irritate
    0.31
     बनी
    0.31
    Act Density 0.000%

    No Known Activations