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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /include
    -0.07
    ']>
    -0.07
    vehicles
    -0.07
    ndl
    -0.06
    ودة
    -0.06
    -centered
    -0.06
     )"
    -0.06
     про
    -0.06
    .Surface
    -0.06
    práv
    -0.06
    POSITIVE LOGITS
    Allows
    0.07
     barely
    0.07
     назнач
    0.06
     DUI
    0.06
     Sandra
    0.06
     carr
    0.06
     Command
    0.06
    	conn
    0.06
     Category
    0.06
     constructing
    0.06
    Act Density 0.053%

    No Known Activations