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

    Neuronpedia

    INDEX
    Explanations

    \` escapes ` . `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rock
    0.38
    illier
    0.37
     to
    0.37
     Adam
    0.37
     through
    0.37
     Z
    0.36
     کوشش
    0.36
    ke
    0.36
     sw
    0.35
    blers
    0.34
    POSITIVE LOGITS
    0.39
    柔軟
    0.35
    LayoutStyle
    0.35
     housewife
    0.34
    ायर
    0.33
    стю
    0.32
     عنا
    0.32
    لوم
    0.32
     внеш
    0.32
    イルス
    0.32
    Act Density 0.002%

    No Known Activations