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

    Neuronpedia

    INDEX
    Explanations

    computational and laners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NaCl
    0.22
     PTSD
    0.22
     bijvoorbeeld
    0.20
    0.20
     സാഹചര്യ
    0.20
     Python
    0.19
     Publikum
    0.19
     $
    0.19
     GDP
    0.19
     ၂
    0.19
    POSITIVE LOGITS
    the
    0.26
    ों
    0.23
    ↵
    0.23
    이
    0.23
    ра
    0.22
    с
    0.21
     của
    0.21
    ं
    0.21
    ك
    0.21
    ای
    0.21
    Act Density 3.294%

    No Known Activations