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

    Neuronpedia

    INDEX
    Explanations

    Code examples and corrections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '),↵
    -0.07
    _cases
    -0.06
     Hari
    -0.06
    ochond
    -0.06
    _don
    -0.06
    ,↵↵
    -0.06
    give
    -0.06
    ,↵
    -0.06
     dealings
    -0.06
     suitability
    -0.06
    POSITIVE LOGITS
     puzz
    0.07
    ™
    0.07
    astically
    0.07
     Тип
    0.07
    (Resource
    0.07
    ...\
    0.06
    �i
    0.06
     UNICODE
    0.06
     flora
    0.06
    政治
    0.06
    Act Density 0.124%

    No Known Activations