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

    Neuronpedia

    INDEX
    Explanations

    years 2020-2050

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !”
    -1.79
     включает
    -1.66
     corrobor
    -1.66
     necessitates
    -1.59
     обеспечивает
    -1.58
    -”
    -1.56
     mani
    -1.55
     hundred
    -1.54
     quell
    -1.53
    ched
    -1.52
    POSITIVE LOGITS
     they
    1.56
    家乡
    1.50
    They
    1.49
    他们
    1.48
    一个
    1.43
     $
    1.43
     "
    1.37
    ،
    1.34
     แต่
    1.34
    You
    1.34
    Act Density 0.005%

    No Known Activations