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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Documents
    -0.08
     whisk
    -0.07
     Thick
    -0.07
     RNG
    -0.06
    万里
    -0.06
    ມ
    -0.06
    TYPO
    -0.06
    以為
    -0.06
    “Yes
    -0.06
    -priced
    -0.06
    POSITIVE LOGITS
    protobuf
    0.08
    sim
    0.07
    争相
    0.07
    скую
    0.07
    깝
    0.07
    _STAR
    0.07
    -scripts
    0.07
    分泌
    0.07
    truck
    0.07
    SX
    0.07
    Act Density 0.001%

    No Known Activations