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

    Neuronpedia

    INDEX
    Explanations

    Test

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    趣
    -0.07
    .MSG
    -0.07
    -compose
    -0.07
    	ax
    -0.07
    _Message
    -0.07
    ousse
    -0.07
    露
    -0.07
     EMS
    -0.07
    RV
    -0.07
    세
    -0.07
    POSITIVE LOGITS
    etermine
    0.08
    ibility
    0.07
     bitmask
    0.07
     shared
    0.07
     ולאחר
    0.07
    認為
    0.07
    盐城
    0.07
    监控
    0.06
     tracks
    0.06
    加盟商
    0.06
    Act Density 0.010%

    No Known Activations