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

    Neuronpedia

    INDEX
    Explanations

    ography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	arr
    -0.07
    .ast
    -0.07
    -Y
    -0.07
     Teaching
    -0.07
     circ
    -0.07
    :");
↵
    -0.07
    قد
    -0.06
    惧
    -0.06
    高三
    -0.06
     CRE
    -0.06
    POSITIVE LOGITS
    -status
    0.07
     paramount
    0.07
    但我
    0.07
    ;,
    0.07
     invented
    0.07
     Sloven
    0.07
     HtmlWebpackPlugin
    0.06
    =tk
    0.06
    Combine
    0.06
    央行
    0.06
    Act Density 0.002%

    No Known Activations