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

    Neuronpedia

    INDEX
    Explanations

    sorting and sieving algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仪表
    0.43
    ان
    0.43
    ጨማሪ
    0.41
    után
    0.40
    رو
    0.40
    𝑟
    0.38
    t
    0.38
    adim
    0.37
    Cafe
    0.37
    GIF
    0.37
    POSITIVE LOGITS
     eminent
    0.43
     listopada
    0.42
     kilometers
    0.41
     Spielen
    0.41
     cint
    0.41
     piedi
    0.41
     उबाल
    0.41
     foglie
    0.41
     enfermed
    0.40
     METAL
    0.40
    Act Density 0.449%

    No Known Activations