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

    Neuronpedia

    INDEX
    Explanations

    from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    闗
    0.38
     either
    0.37
    兩
    0.37
    有两种
    0.37
     અથવા
    0.36
     hoặc
    0.36
     অথবা
    0.36
    either
    0.35
    或者
    0.34
     entweder
    0.34
    POSITIVE LOGITS
     hingga
    0.50
     semplice
    0.50
     έως
    0.50
     simple
    0.50
     sederhana
    0.48
     semplici
    0.48
     लेकर
    0.47
    简单的
    0.47
     downright
    0.46
     እስከ
    0.45
    Act Density 0.131%

    No Known Activations