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

    Neuronpedia

    INDEX
    Explanations

    Code and data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HIP
    -0.07
    handleChange
    -0.07
    /".$
    -0.07
    потен
    -0.06
    closure
    -0.06
     Dubai
    -0.06
    鲳
    -0.06
    Released
    -0.06
    ottenham
    -0.06
    .Accept
    -0.06
    POSITIVE LOGITS
     Wants
    0.08
     librarian
    0.07
    :↵
    0.07
     içinde
    0.07
     exert
    0.07
     Way
    0.07
    سياسة
    0.07
     Bir
    0.07
     Writing
    0.06
    œ
    0.06
    Act Density 0.108%

    No Known Activations