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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    但是我
    0.30
    ون
    0.29
     mutta
    0.27
     grosseur
    0.27
    ،
    0.27
     Nhưng
    0.27
    けど
    0.26
     nhưng
    0.26
     veoma
    0.26
    的代码
    0.25
    POSITIVE LOGITS
     it
    0.43
     there
    0.33
    它
    0.28
    There
    0.27
    there
    0.27
     이는
    0.25
     ისინი
    0.25
    随着
    0.24
     itp
    0.24
    它可以
    0.24
    Act Density 0.453%

    No Known Activations