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

    Neuronpedia

    INDEX
    Explanations

    Code/internet text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     снов
    -0.08
    .qt
    -0.08
    船上
    -0.07
    ㈑
    -0.07
    ╉
    -0.07
    仲裁
    -0.07
    乒乓球
    -0.07
     course
    -0.07
    /event
    -0.07
    住房
    -0.06
    POSITIVE LOGITS
    rysler
    0.08
    	System
    0.07
     leverage
    0.07
    严格
    0.07
    與
    0.07
     fleece
    0.07
    ISTS
    0.07
     amplified
    0.07
    ,ll
    0.07
    Lake
    0.07
    Act Density 0.166%

    No Known Activations