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

    Neuronpedia

    INDEX
    Explanations

    Helsinki

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Montana
    -0.07
    (jLabel
    -0.06
    라
    -0.06
    加载
    -0.06
    orderby
    -0.06
    ке
    -0.06
    енка
    -0.06
    媒体
    -0.06
    raisal
    -0.06
    hana
    -0.06
    POSITIVE LOGITS
    runner
    0.07
     invoking
    0.07
     AB
    0.07
    irthday
    0.06
    (Application
    0.06
     rewrite
    0.06
     consect
    0.06
    halten
    0.06
     innocence
    0.06
    (last
    0.06
    Act Density 0.102%

    No Known Activations