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

    Neuronpedia

    INDEX
    Explanations

    Website comments and reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controvers
    -0.07
     oi
    -0.07
    <translation
    -0.07
     overlooked
    -0.07
    .cursor
    -0.07
     reusable
    -0.07
     sized
    -0.07
    	logger
    -0.07
    EEK
    -0.07
    态
    -0.06
    POSITIVE LOGITS
    𝑆
    0.07
    endTime
    0.07
    决胜
    0.07
    })();↵↵
    0.07
    aset
    0.07
    튜
    0.07
    游戏当中
    0.07
    抓捕
    0.06
    DM
    0.06
     Countdown
    0.06
    Act Density 0.004%

    No Known Activations