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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    composite
    -0.07
    ()}}↵
    -0.07
    <Person
    -0.07
    xdb
    -0.07
     USHORT
    -0.07
    ulfill
    -0.07
    CppMethodPointer
    -0.07
    bones
    -0.06
    俱乐
    -0.06
    navbarSupportedContent
    -0.06
    POSITIVE LOGITS
    (dataset
    0.08
     Label
    0.07
    .sy
    0.07
     �
    0.07
    Tokenizer
    0.07
     terug
    0.07
    完了
    0.06
    (Binary
    0.06
    源于
    0.06
     proclaimed
    0.06
    Act Density 0.020%

    No Known Activations