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

    Neuronpedia

    INDEX
    Explanations

    explain with numbers and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     často
    0.53
     vissa
    0.51
    屢
    0.48
     manchmal
    0.47
    이죠
    0.46
    Certain
    0.44
     kadang
    0.44
     нередко
    0.43
     větš
    0.43
     대부분
    0.43
    POSITIVE LOGITS
     three
    1.08
     five
    0.93
    至少
    0.89
     THREE
    0.85
    three
    0.82
     কমপক্ষে
    0.82
     तीन
    0.81
     two
    0.81
     four
    0.79
     FIVE
    0.78
    Act Density 0.058%

    No Known Activations