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

    Neuronpedia

    INDEX
    Explanations

    social interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。据
    -0.08
     пап
    -0.08
     দাম
    -0.08
     spenn
    -0.08
     llvm
    -0.08
     стратегия
    -0.08
     Entwicklungen
    -0.08
     расходы
    -0.07
     zahlreiche
    -0.07
     எ
    -0.07
    POSITIVE LOGITS
    正式
    0.09
    場合
    0.09
     consens
    0.09
    严
    0.09
    遇
    0.09
     casual
    0.08
     acquaintances
    0.08
    交流
    0.08
    陌
    0.08
     interpersonal
    0.08
    Act Density 0.039%

    No Known Activations