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

    Neuronpedia

    INDEX
    Explanations

    itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    criptive
    0.75
     PRIVATE
    0.66
     private
    0.65
    摊
    0.64
    🗒
    0.64
    hesians
    0.64
     mathvariant
    0.64
    િન
    0.63
     വ്യത്യ
    0.62
     your
    0.61
    POSITIVE LOGITS
     itself
    4.84
     themselves
    4.17
    本身
    3.84
     herself
    3.69
     himself
    3.64
     نفسها
    3.49
    本身的
    3.26
     Himself
    3.13
     نفسه
    3.12
    自体
    3.06
    Act Density 0.425%

    No Known Activations