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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     khoảng
    -0.07
     Basically
    -0.06
    ただ
    -0.06
    .team
    -0.06
    <?>
    -0.06
     cualquier
    -0.06
    .bluetooth
    -0.06
    _goods
    -0.06
    istema
    -0.06
    POSITIVE LOGITS
     nurse
    0.07
    -section
    0.07
     mdi
    0.07
    コード
    0.06
    .Include
    0.06
     Rihanna
    0.06
    ['__
    0.06
     statistics
    0.06
     citizenship
    0.06
     Observable
    0.06
    Act Density 0.001%

    No Known Activations