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

    Neuronpedia

    INDEX
    Explanations

    obtained, acquired, or provided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жна
    0.42
     mView
    0.39
     قلت
    0.39
     solvable
    0.38
     currentNode
    0.38
     diagonalizable
    0.38
     செய்யலாம்
    0.37
    ως
    0.37
    AsStream
    0.37
     ändern
    0.36
    POSITIVE LOGITS
     acquired
    1.50
     obtained
    1.48
     получен
    1.45
     purchased
    1.34
    acquired
    1.31
     Obtained
    1.27
     procured
    1.27
     derived
    1.22
    obtained
    1.20
     created
    1.17
    Act Density 0.027%

    No Known Activations