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

    Neuronpedia

    INDEX
    Explanations

    code statements and blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     없어
    0.40
     ഇടപെ
    0.37
    煒
    0.37
    0.34
    িশালী
    0.34
     hose
    0.33
    弟子
    0.33
    不敢
    0.33
     তাই
    0.32
    watercolor
    0.32
    POSITIVE LOGITS
    ↵
    0.54
     lastly
    0.42
    <0x0D>
    0.41
    acking
    0.40
            
    0.39
    zu
    0.39
    bak
    0.38
    ↵↵
    0.38
    ırmaya
    0.37
                            
    0.37
    Act Density 0.104%

    No Known Activations