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

    Neuronpedia

    INDEX
    Explanations

    sexual connotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <u>
    0.31
    There
    0.30
     There
    0.29
    也可以
    0.27
     phenomenon
    0.26
    lli
    0.26
     Wikipedia
    0.25
    0.25
    <unused2130>
    0.24
     ‌
    0.24
    POSITIVE LOGITS
     مذکور
    0.37
     بیاکتنې
    0.35
     eten
    0.33
     muziek
    0.31
    ເພດ
    0.31
     restantes
    0.31
     cadeaux
    0.31
     różnych
    0.30
     جوړونکي
    0.30
     privind
    0.30
    Act Density 0.154%

    No Known Activations