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

    Neuronpedia

    INDEX
    Explanations

    open curly bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SER
    -0.07
     feat
    -0.07
     Cooke
    -0.07
    .operations
    -0.06
    失败
    -0.06
     gor
    -0.06
     csvfile
    -0.06
     موجب
    -0.06
     DUI
    -0.06
     cytok
    -0.06
    POSITIVE LOGITS
    .ident
    0.07
    ../../
    0.07
    (graph
    0.07
    .which
    0.07
     alan
    0.07
    earth
    0.06
    .ham
    0.06
     asynchronously
    0.06
    .direct
    0.06
    	Model
    0.06
    Act Density 0.001%

    No Known Activations