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

    Neuronpedia

    INDEX
    Explanations

    skip it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Apollo
    0.54
     Virgo
    0.51
    ild
    0.50
    aing
    0.49
     Astro
    0.48
     Th
    0.48
    nd
    0.47
     Schwier
    0.47
     Schwarzschild
    0.46
    ayaan
    0.46
    POSITIVE LOGITS
    خط
    0.47
    سل
    0.47
     часу
    0.46
    スの
    0.45
    Regardless
    0.44
    鍚
    0.44
     جرام
    0.44
    يز
    0.43
     கம
    0.43
     czasu
    0.42
    Act Density 0.000%

    No Known Activations