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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scrambled
    -0.07
    ardi
    -0.07
     rusty
    -0.07
    sen
    -0.07
     attic
    -0.07
    뭇
    -0.07
    enty
    -0.07
    NV
    -0.07
     совершен
    -0.07
    Won
    -0.07
    POSITIVE LOGITS
    宁静
    0.08
    netinet
    0.07
    注明来源
    0.07
     documentation
    0.06
    人流
    0.06
    pj
    0.06
     XPAR
    0.06
    唵
    0.06
    InputDialog
    0.06
     пере
    0.06
    Act Density 0.001%

    No Known Activations