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

    Neuronpedia

    INDEX
    Explanations

    count

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cycle
    -0.08
     lui
    -0.07
     Rome
    -0.07
     bài
    -0.07
     jug
    -0.07
     düzenlenen
    -0.07
     Science
    -0.07
     dù
    -0.06
    .IContainer
    -0.06
     националь
    -0.06
    POSITIVE LOGITS
     Count
    0.08
     Earl
    0.08
     граф
    0.07
     Counts
    0.07
    Ear
    0.07
    มาก
    0.06
     Graf
    0.06
    scanf
    0.06
    roz
    0.06
    open
    0.06
    Act Density 0.006%

    No Known Activations