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

    Neuronpedia

    INDEX
    Explanations

    OS, relinquish, welcome, stopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whats
    0.39
    ഹ്ലാദ
    0.38
    adex
    0.37
     amarelo
    0.37
     ټ
    0.37
     romp
    0.36
    گیرد
    0.36
     harn
    0.35
     redhead
    0.35
    xm
    0.35
    POSITIVE LOGITS
     भी
    0.47
     కూడా
    0.39
     мощности
    0.39
     weitere
    0.38
     weiteren
    0.38
     بھی
    0.36
     अन्य
    0.36
     ইচ্ছ
    0.35
    线性
    0.35
     ஆன்
    0.35
    Act Density 0.000%

    No Known Activations