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

    Neuronpedia

    INDEX
    Explanations

    initialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dataIndex
    -0.08
     CIA
    -0.07
     요
    -0.07
    羁
    -0.07
    EX
    -0.07
    侩
    -0.07
    𝐲
    -0.07
    бря
    -0.07
     getS
    -0.07
    遑
    -0.07
    POSITIVE LOGITS
    装饰
    0.07
     liner
    0.07
    讓他們
    0.07
    _tests
    0.07
    כיכר
    0.06
    硭
    0.06
     spaceship
    0.06
    脱贫攻坚
    0.06
    _POLL
    0.06
     Watching
    0.06
    Act Density 0.018%

    No Known Activations