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

    Neuronpedia

    INDEX
    Explanations

    First

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COMPONENT
    -0.07
    Broad
    -0.06
     spends
    -0.06
     왔
    -0.06
    κος
    -0.06
     Kam
    -0.06
     submar
    -0.06
    Across
    -0.06
     cock
    -0.06
     ump
    -0.06
    POSITIVE LOGITS
    latex
    0.06
    .lastName
    0.06
    _slice
    0.06
    ueva
    0.06
    선
    0.06
     imagin
    0.06
    _invoice
    0.06
     %>
    0.06
     seasoned
    0.06
     fireplace
    0.06
    Act Density 0.002%

    No Known Activations