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

    Neuronpedia

    INDEX
    Explanations

    negative numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাড়ীতে
    0.42
    部份
    0.39
    琯
    0.39
    ध्यान
    0.38
    眷
    0.37
    findContacts
    0.37
    టీఎం
    0.37
     Melanie
    0.37
    隍
    0.37
     졸
    0.36
    POSITIVE LOGITS
     (-
    0.79
     negative
    0.75
     $(-
    0.70
     (-)
    0.67
    ,-
    0.64
    (-
    0.63
    }=-
    0.63
     Negative
    0.63
     =-
    0.61
    Negative
    0.60
    Act Density 0.037%

    No Known Activations