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

    Neuronpedia

    INDEX
    Explanations

    Subsets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fic
    -0.07
     navíc
    -0.07
    还
    -0.07
     Athletic
    -0.07
     minutes
    -0.06
     desks
    -0.06
     Kind
    -0.06
    	JOptionPane
    -0.06
     cruelty
    -0.06
    质量
    -0.06
    POSITIVE LOGITS
     Wass
    0.06
    Blake
    0.06
     borderBottom
    0.06
    (plan
    0.06
    otle
    0.06
     شاه
    0.06
    0.06
    EXTERN
    0.06
     зм
    0.06
    .Syntax
    0.06
    Act Density 0.016%

    No Known Activations