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

    Neuronpedia

    INDEX
    Explanations

    SQL query parts and damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कामा
    0.39
    intestin
    0.37
    PRES
    0.35
     风
    0.35
    ۾
    0.35
     tourisme
    0.35
     온
    0.35
    是要
    0.34
    क्टी
    0.34
     बेसिक
    0.34
    POSITIVE LOGITS
     ${\
    0.43
     ক্ষতি
    0.41
    ${\
    0.40
     harm
    0.38
     ત
    0.37
     Garn
    0.36
     क्षति
    0.36
     overlooking
    0.36
     Pun
    0.35
     Damage
    0.35
    Act Density 0.001%

    No Known Activations