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

    Neuronpedia

    INDEX
    Explanations

    not just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    넹
    0.35
     hoàn
    0.34
     Loc
    0.33
     May
    0.33
     Québec
    0.32
     Physic
    0.32
    但也
    0.32
     nonnegative
    0.32
    嗐
    0.32
     Wetland
    0.31
    POSITIVE LOGITS
     merely
    0.65
    侥
    0.54
     haphazard
    0.50
    仅仅
    0.50
    僥
    0.48
    只是
    0.48
     mere
    0.45
     cualquier
    0.44
     단순히
    0.44
     просто
    0.43
    Act Density 0.311%

    No Known Activations