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

    Neuronpedia

    INDEX
    Explanations

    comparing models, programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इत्यादी
    0.41
     কথাও
    0.37
     కూడా
    0.36
     nejen
    0.36
     देखील
    0.35
     επίσης
    0.34
     également
    0.33
     таксама
    0.33
    <unused1068>
    0.33
     همین
    0.33
    POSITIVE LOGITS
    :
    0.48
    ：
    0.42
    の方は
    0.38
     (
    0.36
     VS
    0.34
    还好
    0.34
     -
    0.33
     boasts
    0.33
    は
    0.33
    の場合
    0.31
    Act Density 0.748%

    No Known Activations