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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     достой
    -0.08
     wholes
    -0.08
     amin
    -0.08
     whan
    -0.08
     когато
    -0.07
    ување
    -0.07
    בודה
    -0.07
    \CMS
    -0.07
     पूरा
    -0.07
     CW
    -0.07
    POSITIVE LOGITS
     hashmap
    0.12
     Trie
    0.11
    Trie
    0.11
     dictionary
    0.11
    dictionary
    0.10
     Dictionaries
    0.10
    (dictionary
    0.10
     хранения
    0.09
     dictionaries
    0.09
    .dict
    0.09
    Act Density 0.007%

    No Known Activations