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

    Neuronpedia

    INDEX
    Explanations

    output to files or screen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     явления
    0.40
     పద
    0.39
     прось
    0.39
     زمانہ
    0.39
    jdk
    0.38
     स्वातंत्र
    0.38
    чь
    0.38
    tileSize
    0.38
     سلسلے
    0.38
    ármaz
    0.38
    POSITIVE LOGITS
     coffers
    0.64
     databases
    0.55
     repositories
    0.55
     database
    0.54
     containers
    0.54
     inbox
    0.53
     repository
    0.52
     designated
    0.52
     tables
    0.51
    データベース
    0.50
    Act Density 0.214%

    No Known Activations