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

    Neuronpedia

    INDEX
    Explanations

    package.json code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wield
    -0.08
    bitcoin
    -0.08
    UINT
    -0.08
    ittest
    -0.07
    ите
    -0.07
    グループ
    -0.07
    LOGIN
    -0.07
    homme
    -0.07
    pegawai
    -0.07
    TouchEvent
    -0.07
    POSITIVE LOGITS
    =";↵
    0.08
    促进了
    0.07
     `;↵
    0.07
    -directed
    0.07
     😉↵↵
    0.07
    �
    0.06
    dao
    0.06
     throughout
    0.06
    🌝
    0.06
    始建
    0.06
    Act Density 0.004%

    No Known Activations