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

    Neuronpedia

    INDEX
    Explanations

    remove, removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    விரி
    0.45
    मेरा
    0.43
     iphdr
    0.40
    Doesn
    0.39
     ইনডাক
    0.39
     Wouldn
    0.39
     কোর্স
    0.38
     Wasn
    0.38
    Wouldn
    0.38
     Overlay
    0.38
    POSITIVE LOGITS
     removed
    0.55
     remove
    0.46
     removal
    0.45
     removing
    0.45
     removals
    0.43
     rightful
    0.41
     dates
    0.41
     sub
    0.41
     удаления
    0.40
     specific
    0.39
    Act Density 0.000%

    No Known Activations