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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pair
    -0.07
    "In
    -0.07
     unordered
    -0.07
    书中
    -0.07
     subsection
    -0.07
    .setBackground
    -0.07
     haystack
    -0.07
    .named
    -0.06
     devastating
    -0.06
    -byte
    -0.06
    POSITIVE LOGITS
    ⏤
    0.07
    uzzle
    0.06
     Matchers
    0.06
    🔴
    0.06
     intercourse
    0.06
    ocoa
    0.06
    .static
    0.06
    Quiz
    0.06
    🥞
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations