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

    Neuronpedia

    INDEX
    Explanations

    animal studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    transfer
    -0.07
     defense
    -0.07
    财
    -0.07
     File
    -0.07
    	Register
    -0.06
    景德
    -0.06
    .toUpperCase
    -0.06
     migration
    -0.06
     Journey
    -0.06
     domicile
    -0.06
    POSITIVE LOGITS
    服务器
    0.07
     clearer
    0.07
     rins
    0.06
    仑
    0.06
    /results
    0.06
    _proj
    0.06
    ettle
    0.06
    🔌
    0.06
     uống
    0.06
    структур
    0.06
    Act Density 0.004%

    No Known Activations