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

    Neuronpedia

    INDEX
    Explanations

    biological vs. non-biological

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     İşte
    0.45
     Peker
    0.44
     olmak
    0.43
     olur
    0.42
     강의
    0.41
     Oggi
    0.40
     başlat
    0.39
     штат
    0.39
     채
    0.39
     земля
    0.39
    POSITIVE LOGITS
    neat
    0.50
    പ്പുറ
    0.44
    atable
    0.43
    Pipeline
    0.43
     (
    0.42
    ueness
    0.41
     सक्सेना
    0.39
    耗
    0.39
    ax
    0.38
    Ly
    0.38
    Act Density 0.000%

    No Known Activations