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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    三百
    0.53
     eighteenth
    0.51
     twelfth
    0.51
    第六
    0.49
     eleventh
    0.48
    १८४
    0.48
    Fifth
    0.47
     fourteenth
    0.47
    四十
    0.46
     ৫৮
    0.46
    POSITIVE LOGITS
     पड़े
    0.34
     remove
    0.33
     Removal
    0.32
     саны
    0.31
     Remove
    0.31
    闷
    0.31
     Bal
    0.31
     dwRes
    0.31
     Par
    0.30
     Soa
    0.30
    Act Density 0.706%

    No Known Activations