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

    Neuronpedia

    INDEX
    Explanations

    cybersecurity vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kulay
    -0.08
     pellets
    -0.08
     girls
    -0.08
     Pump
    -0.08
     skill
    -0.08
     மாத
    -0.08
     pump
    -0.07
     purple
    -0.07
     extérieur
    -0.07
     dye
    -0.07
    POSITIVE LOGITS
    多数
    0.09
     metadata
    0.09
     catalog
    0.08
    Metadata
    0.08
    enci
    0.08
     catalogue
    0.08
    Catalog
    0.08
    metadata
    0.08
    编号
    0.08
    _metadata
    0.08
    Act Density 0.003%

    No Known Activations