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

    Neuronpedia

    INDEX
    Explanations

    Code/Formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sum
    -0.08
     cedar
    -0.06
    <Node
    -0.06
    Processes
    -0.06
    emony
    -0.06
    WindowSize
    -0.06
     »↵
    -0.06
    .items
    -0.06
    Plate
    -0.06
     chair
    -0.06
    POSITIVE LOGITS
     ماد
    0.06
    (Context
    0.06
     crank
    0.06
     Анг
    0.06
     MLM
    0.06
    (progress
    0.06
     ZERO
    0.06
     玩家
    0.06
     đa
    0.06
    (any
    0.06
    Act Density 0.240%

    No Known Activations