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

    Neuronpedia

    INDEX
    Explanations

    Negation and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agenta
    -0.07
    Expires
    -0.07
     زند
    -0.07
     ژانویه
    -0.07
    longitude
    -0.07
     SendMessage
    -0.06
    قق
    -0.06
     oversees
    -0.06
    АТ
    -0.06
    Gui
    -0.06
    POSITIVE LOGITS
     ''),↵
    0.07
    .n
    0.07
     phản
    0.06
     �
    0.06
     abst
    0.06
     assert
    0.06
     一
    0.06
     analyzer
    0.06
     ciudad
    0.06
    '),↵
    0.06
    Act Density 0.064%

    No Known Activations