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

    Neuronpedia

    INDEX
    Explanations

    Quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Inner
    -0.06
     Sunni
    -0.06
    treeview
    -0.06
     更新
    -0.06
     Klaus
    -0.06
     외부
    -0.06
     Start
    -0.06
     شع
    -0.06
    hea
    -0.06
     Zimmer
    -0.06
    POSITIVE LOGITS
    ,q
    0.08
    veh
    0.07
     nel
    0.06
     suspicious
    0.06
     buyer
    0.06
     гар
    0.06
     pracov
    0.06
    >):
    0.06
    �
    0.06
     german
    0.06
    Act Density 0.058%

    No Known Activations