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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    share
    -0.06
     millennials
    -0.06
    .ToolStripButton
    -0.06
    AnimationsModule
    -0.06
    临
    -0.06
    Deprecated
    -0.06
     androidx
    -0.05
     прох
    -0.05
    ilter
    -0.05
     moreover
    -0.05
    POSITIVE LOGITS
    lon
    0.08
    encion
    0.07
    aza
    0.07
     max
    0.07
    ΙΚ
    0.07
    焼
    0.06
     Bradley
    0.06
    ayın
    0.06
    الف
    0.06
     ┃
    0.06
    Act Density 0.001%

    No Known Activations