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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     razor
    -0.07
     forwarding
    -0.06
     breaking
    -0.06
    view
    -0.06
     Depot
    -0.06
     penalties
    -0.06
    _thresh
    -0.06
     Briggs
    -0.06
     xmax
    -0.06
     laptops
    -0.06
    POSITIVE LOGITS
     elements
    0.15
     Elements
    0.11
     element
    0.11
     elementos
    0.10
     swirling
    0.08
    elements
    0.07
     elle
    0.07
     Element
    0.07
    Element
    0.07
    .ToolStripMenuItem
    0.07
    Act Density 0.015%

    No Known Activations