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

    Neuronpedia

    INDEX
    Explanations

    vir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三项
    -0.08
     Heard
    -0.08
    legend
    -0.08
    //
    -0.07
     Dane
    -0.07
    Sz
    -0.07
    _side
    -0.07
    写字楼
    -0.07
    abbreviation
    -0.07
    عضو
    -0.07
    POSITIVE LOGITS
     vir
    0.07
    使其
    0.07
     exceed
    0.07
    .RequestMethod
    0.07
    	RE
    0.07
    发送
    0.07
     violate
    0.07
    工业园区
    0.07
     yab
    0.07
     proper
    0.06
    Act Density 0.006%

    No Known Activations