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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    唠
    -0.08
    _shared
    -0.07
    .Pe
    -0.07
     subway
    -0.07
    Retrieve
    -0.07
     Casinos
    -0.06
     Hudson
    -0.06
     warehouses
    -0.06
    angling
    -0.06
     manga
    -0.06
    POSITIVE LOGITS
     Isles
    0.09
     xOffset
    0.07
    ãi
    0.07
     <>
    0.06
    刭
    0.06
    הק
    0.06
    item
    0.06
     cheek
    0.06
     окру
    0.06
    みたい
    0.06
    Act Density 0.084%

    No Known Activations