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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ling
    -0.07
    \admin
    -0.06
     distingu
    -0.06
     завдання
    -0.06
     getEmail
    -0.06
    folders
    -0.06
     часа
    -0.06
    radouro
    -0.06
     rival
    -0.06
    /framework
    -0.06
    POSITIVE LOGITS
    (ids
    0.06
    Soap
    0.06
    _listing
    0.06
    丹
    0.06
    ="<<
    0.06
     STORE
    0.06
    ERİ
    0.06
    PLAY
    0.06
    τια
    0.06
    mination
    0.06
    Act Density 0.001%

    No Known Activations